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

    Neuronpedia

    INDEX
    Explanations

    Organizations/Communities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ès
    -0.08
     Cottage
    -0.08
    רצה
    -0.07
    𬶭
    -0.07
    酒业
    -0.07
    智能化
    -0.07
     thuis
    -0.07
    -minded
    -0.07
    휑
    -0.06
    inded
    -0.06
    POSITIVE LOGITS
    REDENTIAL
    0.07
     guardian
    0.07
    $/,↵
    0.07
     Katherine
    0.06
    Н
    0.06
    镣
    0.06
     nền
    0.06
    ↵↵
    0.06
     repet
    0.06
     dere
    0.06
    Act Density 0.020%

    No Known Activations