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

    Neuronpedia

    INDEX
    Explanations

    ruthless

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nostalgic
    -0.07
    iar
    -0.06
     owl
    -0.06
     realizado
    -0.06
    학회
    -0.06
     вибор
    -0.06
    وق
    -0.06
    .Level
    -0.06
     rainy
    -0.06
    gmail
    -0.06
    POSITIVE LOGITS
    ,“
    0.07
    }";↵
    0.07
    external
    0.07
    _RECE
    0.07
    ="""
    0.07
    	reload
    0.06
    getBody
    0.06
    uffles
    0.06
    \"";↵
    0.06
    INDOW
    0.06
    Act Density 0.023%

    No Known Activations