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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اذا
    -0.07
    _MT
    -0.06
    rylic
    -0.06
     introduced
    -0.06
            
    -0.06
     threat
    -0.06
    -delay
    -0.06
    (pro
    -0.06
    perc
    -0.06
     протяж
    -0.06
    POSITIVE LOGITS
    igslist
    0.07
     PodsDummy
    0.07
    <Any
    0.06
    ii
    0.06
    [length
    0.06
    /kubernetes
    0.06
    (DialogInterface
    0.06
    mayı
    0.06
    (ml
    0.06
     plays
    0.06
    Act Density 0.000%

    No Known Activations