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

    Neuronpedia

    INDEX
    Explanations

    laws restrictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     balanced
    -0.07
    Kn
    -0.07
    дат
    -0.06
    ifferential
    -0.06
    ёр
    -0.06
     ترجم
    -0.06
    ى
    -0.06
     деятель
    -0.06
    ordinal
    -0.06
    ARK
    -0.06
    POSITIVE LOGITS
     setting
    0.07
     Exploration
    0.06
    	frame
    0.06
     пад
    0.06
    .getInstance
    0.06
     surv
    0.06
     Suriye
    0.06
     abbiamo
    0.06
     เร
    0.06
     prostituerte
    0.06
    Act Density 0.022%

    No Known Activations