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

    Neuronpedia

    INDEX
    Explanations

    xx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IDD
    -0.07
     tedavi
    -0.07
     interactions
    -0.07
    efa
    -0.07
     éxito
    -0.06
     доктор
    -0.06
    .ops
    -0.06
    ).\
    -0.06
     alunos
    -0.06
     Buildings
    -0.06
    POSITIVE LOGITS
    Minute
    0.07
    Những
    0.07
    .Val
    0.06
    Roll
    0.06
     CLAIM
    0.06
     Pref
    0.06
    -ie
    0.06
    mıştı
    0.06
     unusually
    0.06
     součas
    0.06
    Act Density 0.003%

    No Known Activations