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

    Neuronpedia

    INDEX
    Explanations

    parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fet
    -0.07
    ойчив
    -0.06
     FT
    -0.06
     पक
    -0.06
     vista
    -0.06
     compensated
    -0.06
    Needed
    -0.06
     Nos
    -0.06
    _ICON
    -0.06
    Weights
    -0.06
    POSITIVE LOGITS
    :numel
    0.07
     سی
    0.06
    cname
    0.06
     Character
    0.06
     Hmm
    0.06
     isEqual
    0.06
     považ
    0.06
    埃
    0.06
    koli
    0.06
     occas
    0.06
    Act Density 0.005%

    No Known Activations