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

    Neuronpedia

    INDEX
    Explanations

    commas and apostrophes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _USED
    -0.07
     Defensive
    -0.06
    VC
    -0.06
    Reg
    -0.06
     votre
    -0.06
    аніт
    -0.06
     NIR
    -0.06
     ██
    -0.06
    alace
    -0.06
    vou
    -0.06
    POSITIVE LOGITS
    540
    0.07
    거
    0.06
    dney
    0.06
    niest
    0.06
     median
    0.06
    akash
    0.06
    -grow
    0.06
     fail
    0.06
    dam
    0.06
     точно
    0.06
    Act Density 0.006%

    No Known Activations