Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical descriptions and processes related to user interfaces or electronic devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following words such as "you", "must", "shall", or "is"

    np_acts-logits-general · gemini-2.0-flash

    shall see, genocide of, must be, data identifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chré
    -0.81
    いろいろな
    -0.77
     colère
    -0.77
     usato
    -0.77
     lots
    -0.77
     banget
    -0.76
    Lots
    -0.75
     really
    -0.75
     usati
    -0.74
     stuff
    -0.72
    POSITIVE LOGITS
    已然
    1.03
     requisite
    0.98
     herein
    0.98
     iż
    0.92
     gänzlich
    0.92
     therein
    0.91
     annum
    0.91
    に於
    0.90
     אשר
    0.90
    倘
    0.89
    Act Density 2.271%

    No Known Activations