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

    Neuronpedia

    INDEX
    Explanations

    say "or" ending

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    ,right
    -0.07
    ircuit
    -0.07
    祇
    -0.07
     peaked
    -0.06
     ancestor
    -0.06
    LICENSE
    -0.06
     gated
    -0.06
     ctor
    -0.06
    蛄
    -0.06
    产学研
    -0.06
    POSITIVE LOGITS
    assignments
    0.07
    _handle
    0.07
     Abd
    0.07
    ummies
    0.06
    לב
    0.06
    pn
    0.06
    enabled
    0.06
    שפ
    0.06
    迈
    0.06
    啷
    0.06
    Act Density 0.152%

    No Known Activations