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

    Neuronpedia

    INDEX
    Explanations

    gene

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     respective
    -0.06
     repair
    -0.06
     відсут
    -0.06
     bombs
    -0.06
     підпис
    -0.06
    娘
    -0.06
    portrait
    -0.06
     fucking
    -0.06
     reps
    -0.06
     generators
    -0.06
    POSITIVE LOGITS
    ================================================================
    0.07
    ála
    0.07
    [int
    0.07
    encer
    0.06
     học
    0.06
    .SaveChangesAsync
    0.06
    เธอ
    0.06
    _DATABASE
    0.06
     olmuştur
    0.06
    া�
    0.06
    Act Density 0.248%

    No Known Activations