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
     Slave
    -0.07
     Investment
    -0.06
    。↵↵
    -0.06
    νώ
    -0.06
    avier
    -0.06
    ({});↵
    -0.06
    Wrong
    -0.06
     contradictory
    -0.06
    凝
    -0.06
    $str
    -0.06
    POSITIVE LOGITS
     ss
    0.06
     sch
    0.06
     lik
    0.06
     eliminar
    0.06
    (delegate
    0.06
    部分
    0.06
    104
    0.06
    rát
    0.06
    (global
    0.06
    さんは
    0.06
    Act Density 0.002%

    No Known Activations