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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     шир
    -0.07
    าะห
    -0.06
    呼
    -0.06
    Rp
    -0.06
     histor
    -0.06
     priest
    -0.06
    ेल
    -0.06
     posY
    -0.06
     murderers
    -0.06
    lä
    -0.06
    POSITIVE LOGITS
    		 ↵
    0.06
     gönder
    0.06
    えて
    0.06
     Chicago
    0.06
    а
    0.06
    letion
    0.06
     CHARSET
    0.06
     Michelle
    0.06
     charset
    0.06
     dbname
    0.06
    Act Density 0.003%

    No Known Activations