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

    Neuronpedia

    INDEX
    Explanations

    instinct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ες
    1.24
    تي
    1.23
    ной
    1.18
    issait
    1.15
    ovali
    1.13
    ти
    1.11
     conceivably
    1.11
    ඬ
    1.09
    Υ
    1.09
    िज
    1.08
    POSITIVE LOGITS
    적으로
    1.56
     -------------
    1.23
    ively
    1.21
    るので
    1.21
     Instinct
    1.21
     وفي
    1.19
     человека
    1.18
    어서
    1.17
    .
    1.14
     nisid
    1.13
    Act Density 0.126%

    No Known Activations