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

    Neuronpedia

    INDEX
    Explanations

    me

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hogy
    -0.06
     něho
    -0.06
     Knock
    -0.06
    erre
    -0.06
     Welfare
    -0.06
    /repos
    -0.06
     Bernie
    -0.06
    .gs
    -0.06
    _mv
    -0.06
     различные
    -0.06
    POSITIVE LOGITS
    perform
    0.07
    bigint
    0.06
     Locate
    0.06
    lk
    0.06
     TOK
    0.06
     SECRET
    0.06
     opt
    0.06
     songs
    0.06
     PER
    0.06
     امر
    0.06
    Act Density 0.000%

    No Known Activations