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

    Neuronpedia

    INDEX
    Explanations

    questions about what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     již
    0.75
    已經
    0.70
    已经是
    0.69
    已
    0.67
    较为
    0.66
    りと
    0.66
    並不
    0.66
    わず
    0.64
     might
    0.64
     менее
    0.64
    POSITIVE LOGITS
     แนะ
    0.78
     Photoc
    0.69
    头像
    0.68
     Sewage
    0.67
    !;
    0.66
     radar
    0.65
    Pension
    0.65
     montaje
    0.64
     sewage
    0.64
     Vaccination
    0.63
    Act Density 0.040%

    No Known Activations