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

    Neuronpedia

    INDEX
    Explanations

    indicators of absence or presence related to physical or mental symptoms

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

    sign of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    department
    -0.32
     justa
    -0.31
    bestimmungen
    -0.31
     department
    -0.30
    because
    -0.30
    typedef
    -0.29
    ชน
    -0.29
     departments
    -0.28
     Department
    -0.28
    Department
    -0.27
    POSITIVE LOGITS
     traces
    0.86
     Traces
    0.86
     trace
    0.79
     TRACE
    0.73
    traces
    0.71
     Spuren
    0.71
    Traces
    0.69
     Trace
    0.68
     traccia
    0.67
     informée
    0.66
    Act Density 0.036%

    No Known Activations