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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _border
    -0.08
     Validates
    -0.07
     España
    -0.07
    =query
    -0.07
    ounded
    -0.07
     dedication
    -0.07
     Disclosure
    -0.07
     violations
    -0.06
    adaş
    -0.06
     revelation
    -0.06
    POSITIVE LOGITS
    fone
    0.08
     thôn
    0.07
    _indx
    0.07
    ᶇ
    0.07
     toughness
    0.07
    'Brien
    0.07
     Nine
    0.07
    _Run
    0.06
    𝘄
    0.06
    瀏
    0.06
    Act Density 0.056%

    No Known Activations