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

    Neuronpedia

    INDEX
    Explanations

    specific medical or experimental outcomes and their measurements

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

    a consequence or outcome

    np_acts-logits-general · gemini-2.0-flash

    existence or occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     who
    -0.50
    ところです
    -0.48
    tvguidetime
    -0.46
    干
    -0.45
    ">',
    -0.44
     hany
    -0.43
    ：“……”
    -0.42
    ("")]
    -0.42
    вов
    -0.41
     raff
    -0.41
    POSITIVE LOGITS
     exists
    1.22
     ensued
    1.10
     exist
    1.07
     existed
    1.03
     ensues
    1.02
     occurred
    0.96
     occurs
    0.88
     Exists
    0.88
     fanns
    0.87
     prevails
    0.86
    Act Density 0.929%

    No Known Activations