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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     turf
    -0.07
    漫步
    -0.07
    uche
    -0.07
    契机
    -0.06
    aviors
    -0.06
    anted
    -0.06
     הראשון
    -0.06
    anych
    -0.06
    mmc
    -0.06
    茸
    -0.06
    POSITIVE LOGITS
    فيد
    0.07
     inspect
    0.06
    �
    0.06
    .fire
    0.06
    .LayoutStyle
    0.06
     OSP
    0.06
     требова
    0.06
     gerekt
    0.06
    .details
    0.06
    斶
    0.06
    Act Density 0.001%

    No Known Activations