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

    Neuronpedia

    INDEX
    Explanations

    css

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    主义
    -0.07
    announce
    -0.07
     این
    -0.07
    �
    -0.07
    ::<
    -0.06
     Those
    -0.06
     часть
    -0.06
    Resultado
    -0.06
    }))↵
    -0.06
    _inicio
    -0.06
    POSITIVE LOGITS
    Adventure
    0.07
     REFER
    0.07
     dispro
    0.06
     comput
    0.06
    York
    0.06
    Bus
    0.06
    event
    0.06
     uniformly
    0.06
    enguin
    0.06
    αρ
    0.06
    Act Density 0.004%

    No Known Activations