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

    Neuronpedia

    INDEX
    Explanations

    iterator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tact
    -0.07
    צו
    -0.07
     deliberately
    -0.07
    ﺬ
    -0.07
    爨
    -0.07
    졪
    -0.07
    คาด
    -0.07
     dangerously
    -0.06
    细节
    -0.06
    /stats
    -0.06
    POSITIVE LOGITS
     Vocal
    0.07
     Connected
    0.07
     declining
    0.07
     orbs
    0.07
    Cols
    0.07
    _sub
    0.07
     Seit
    0.06
    0.06
     Quad
    0.06
    วด
    0.06
    Act Density 0.009%

    No Known Activations