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

    Neuronpedia

    INDEX
    Explanations

    Ten, anus, Claim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Coral
    0.49
    猞
    0.48
    रो
    0.48
     நம
    0.47
    小孩
    0.47
    锌
    0.46
    la
    0.46
    离子
    0.46
     الدم
    0.45
     Kul
    0.45
    POSITIVE LOGITS
    ohnt
    0.48
     offenen
    0.47
    KNOWN
    0.45
    equivalent
    0.43
    prisingly
    0.43
    VarArgs
    0.43
    жы
    0.43
    erves
    0.41
    แรก
    0.41
    izes
    0.41
    Act Density 0.002%

    No Known Activations