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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IRC
    -0.06
    ibly
    -0.06
     Lud
    -0.06
    _continue
    -0.06
    EDIATE
    -0.06
     Kad
    -0.06
    _start
    -0.06
    Msg
    -0.06
    洛
    -0.06
    опол
    -0.06
    POSITIVE LOGITS
     the
    0.07
    (as
    0.07
     provided
    0.07
    可以
    0.07
     χ
    0.06
    不同
    0.06
    हम
    0.06
     것도
    0.06
     reminis
    0.06
    ों,
    0.06
    Act Density 0.044%

    No Known Activations