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

    Neuronpedia

    INDEX
    Explanations

    rule

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VERRIDE
    -0.06
     Doğum
    -0.06
    ям
    -0.06
     democracy
    -0.06
    ュー
    -0.06
    -trash
    -0.06
     fifteen
    -0.06
     thirteen
    -0.06
    xed
    -0.06
    entries
    -0.06
    POSITIVE LOGITS
    ặc
    0.07
     rid
    0.07
     сез
    0.07
     implic
    0.07
    р
    0.06
     moving
    0.06
     enorm
    0.06
     relic
    0.06
    .concat
    0.06
     Alumni
    0.06
    Act Density 0.000%

    No Known Activations