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

    Neuronpedia

    INDEX
    Explanations

    Medical research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ALIGNMENT
    -0.06
    ولو
    -0.06
    Š
    -0.06
    _ANY
    -0.06
     Tutor
    -0.06
    服
    -0.06
    _dim
    -0.06
    xed
    -0.06
     kırmızı
    -0.06
    _strlen
    -0.06
    POSITIVE LOGITS
     accuses
    0.06
     براى
    0.06
     اه
    0.06
     работать
    0.06
    hashed
    0.06
     roční
    0.06
    原因
    0.06
     arity
    0.06
     intimately
    0.06
    altern
    0.06
    Act Density 0.019%

    No Known Activations