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

    Neuronpedia

    INDEX
    Explanations

    Lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pot
    -0.06
    porn
    -0.06
     flee
    -0.06
    Выб
    -0.06
     binary
    -0.06
    Alternate
    -0.06
     GOLD
    -0.06
    हल
    -0.06
    Res
    -0.06
    	res
    -0.06
    POSITIVE LOGITS
    ablytyped
    0.07
    izin
    0.07
    ありが
    0.07
    ercises
    0.06
    <Message
    0.06
    agens
    0.06
    vtColor
    0.06
     hust
    0.06
     města
    0.06
     vede
    0.06
    Act Density 0.064%

    No Known Activations