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

    Neuronpedia

    INDEX
    Explanations

    terms related to physics measurements and theoretical frameworks

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

    Comes before words like "help", "shown", "find", "realiz"

    np_acts-logits-general · gemini-2.0-flash

    experimental findings and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    copyOf
    -0.45
     Movement
    -0.44
     paja
    -0.43
     ladri
    -0.43
     Rock
    -0.43
    }}_
    -0.42
     kult
    -0.41
     hotel
    -0.41
     Cara
    -0.40
    struk
    -0.39
    POSITIVE LOGITS
    Portail
    1.00
     betweenstory
    0.95
    DockStyle
    0.90
    TagMode
    0.88
     autorytatywna
    0.87
     Walkover
    0.86
     propOrder
    0.84
    存于互联网档案馆
    0.82
     Monfieur
    0.80
    Portale
    0.80
    Act Density 5.806%

    No Known Activations