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
     теперь
    -0.06
     impairment
    -0.06
     материал
    -0.06
     Timestamp
    -0.06
     ADC
    -0.06
     loans
    -0.06
     مک
    -0.06
    _az
    -0.06
     unst
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    itmap
    0.07
    тура
    0.07
    )—
    0.06
     […
    0.06
    ALIGN
    0.06
    ité
    0.06
    scalar
    0.06
     slicing
    0.06
    :SetText
    0.06
    .IC
    0.06
    Act Density 0.000%

    No Known Activations