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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    datos
    -0.07
    .valor
    -0.07
     deserve
    -0.07
    ��
    -0.07
    _damage
    -0.06
    aria
    -0.06
    -arrow
    -0.06
    312
    -0.06
     shocking
    -0.06
     silly
    -0.06
    POSITIVE LOGITS
    anchise
    0.08
     controlling
    0.07
     Pred
    0.07
     Diff
    0.07
    apl
    0.06
    бот
    0.06
     Cond
    0.06
     Petro
    0.06
    measurement
    0.06
    .aspect
    0.06
    Act Density 0.001%

    No Known Activations