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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     datas
    -0.07
    以为
    -0.06
    _distances
    -0.06
    aram
    -0.06
    Controls
    -0.06
    Todos
    -0.06
    _BS
    -0.06
    param
    -0.06
    cmds
    -0.06
    Reached
    -0.06
    POSITIVE LOGITS
     İt
    0.07
    jing
    0.06
     lm
    0.06
     Equ
    0.06
    lak
    0.06
     Goat
    0.06
     Film
    0.06
    (EVENT
    0.06
    unuz
    0.06
     Lindsay
    0.06
    Act Density 0.000%

    No Known Activations