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

    Neuronpedia

    INDEX
    Explanations

    Loading, starting up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    😈
    -0.07
    =https
    -0.07
    ollision
    -0.07
    isAdmin
    -0.07
    箴
    -0.07
    >↵↵↵
    -0.07
     heater
    -0.07
     lone
    -0.06
    .setTag
    -0.06
     представляет
    -0.06
    POSITIVE LOGITS
     '%$
    0.07
    Pk
    0.07
    عباد
    0.07
    들과
    0.07
     רבות
    0.07
     prominent
    0.07
    (variable
    0.07
    avar
    0.07
    nob
    0.07
    istros
    0.06
    Act Density 0.096%

    No Known Activations