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

    Neuronpedia

    INDEX
    Explanations

    upstream

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Severity
    -0.07
     Daly
    -0.07
     добре
    -0.07
     holidays
    -0.06
    Little
    -0.06
    (BigInteger
    -0.06
     Pie
    -0.06
     spiritual
    -0.06
     pouco
    -0.06
     severity
    -0.06
    POSITIVE LOGITS
    ुट
    0.07
     стороны
    0.06
    <u
    0.06
    PRICE
    0.06
     Hitch
    0.06
     invokevirtual
    0.06
     sockfd
    0.06
    enk
    0.06
    	bytes
    0.06
    ering
    0.06
    Act Density 0.005%

    No Known Activations