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
    '.↵
    -0.08
    .Validate
    -0.07
    icult
    -0.07
    _when
    -0.07
    (long
    -0.07
    Unless
    -0.07
     Miles
    -0.07
     Bộ
    -0.06
    Kal
    -0.06
     Ginger
    -0.06
    POSITIVE LOGITS
    作り
    0.07
    .before
    0.07
    książ
    0.07
     educación
    0.07
    死了
    0.06
    ਸ
    0.06
    腻
    0.06
    ador
    0.06
     nearer
    0.06
    דור
    0.06
    Act Density 0.001%

    No Known Activations