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

    Neuronpedia

    INDEX
    Explanations

    boost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .od
    -0.07
    OMBRE
    -0.07
     raped
    -0.07
    .Err
    -0.06
    igua
    -0.06
    (prob
    -0.06
    _RESERVED
    -0.06
    flake
    -0.06
    (v
    -0.06
     ओर
    -0.06
    POSITIVE LOGITS
     polls
    0.07
     bolster
    0.07
    	input
    0.07
     astr
    0.06
     قتل
    0.06
    _strlen
    0.06
    CGFloat
    0.06
    _touch
    0.06
    digital
    0.06
    hil
    0.06
    Act Density 0.019%

    No Known Activations