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

    Neuronpedia

    INDEX
    Explanations

    Freelancing platforms

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
     experiencing
    -0.08
    _SOL
    -0.08
    [item
    -0.07
    据报道
    -0.07
    '])[
    -0.07
    嵛
    -0.07
    .Location
    -0.07
    CHR
    -0.06
     znalazł
    -0.06
    .readline
    -0.06
    POSITIVE LOGITS
     Perfect
    0.07
    פע
    0.07
    ייס
    0.07
    .NOT
    0.07
    аз
    0.06
    _ITER
    0.06
    _F
    0.06
     Cross
    0.06
     Eye
    0.06
    峰
    0.06
    Act Density 0.046%

    No Known Activations