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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proceso
    -0.07
    발
    -0.06
    лий
    -0.06
     morale
    -0.06
    错误
    -0.06
    Ass
    -0.06
    piration
    -0.06
    foreign
    -0.06
    (fr
    -0.06
     perso
    -0.06
    POSITIVE LOGITS
    ोख
    0.07
     Sunderland
    0.07
     murderers
    0.06
     Ashe
    0.06
    상을
    0.06
    Effect
    0.06
     cousin
    0.06
    IONS
    0.06
    Furthermore
    0.06
    _pair
    0.06
    Act Density 0.059%

    No Known Activations