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

    Neuronpedia

    INDEX
    Explanations

    advertisements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Localized
    -0.06
    ायत
    -0.06
    .getChannel
    -0.06
     �
    -0.06
    Tcp
    -0.06
    š
    -0.06
     fracture
    -0.06
    :
↵
    -0.06
     mural
    -0.06
    tokenizer
    -0.06
    POSITIVE LOGITS
    REFER
    0.06
    čas
    0.06
    يكي
    0.06
    STEM
    0.06
     asiat
    0.06
    Safety
    0.06
    makt
    0.06
     figura
    0.06
    enance
    0.06
    тие
    0.06
    Act Density 0.032%

    No Known Activations