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

    Neuronpedia

    INDEX
    Explanations

    proactive approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lorsque
    0.42
     anthropologist
    0.42
     theologian
    0.41
    とした
    0.40
    思う
    0.38
    Ķ
    0.38
    羙
    0.37
    ویی
    0.36
     {$
    0.35
     时
    0.35
    POSITIVE LOGITS
     jacuzzi
    0.46
    কাতার
    0.42
     другом
    0.41
    បន្ទ
    0.41
    target
    0.40
    sour
    0.40
     terraza
    0.40
     ALG
    0.39
    issu
    0.39
     sour
    0.39
    Act Density 0.002%

    No Known Activations