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

    Neuronpedia

    INDEX
    Explanations

    say "t" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    衩
    -0.07
    一点
    -0.07
    _SECURE
    -0.07
    clud
    -0.07
    建て
    -0.06
    遛
    -0.06
    出轨
    -0.06
    挺
    -0.06
    �
    -0.06
    posit
    -0.06
    POSITIVE LOGITS
     genomic
    0.08
     glorious
    0.07
     :]
    0.07
    "]]
    0.07
    バン
    0.07
     Timothy
    0.07
     saliva
    0.06
     Seth
    0.06
    ();
↵
↵
    0.06
    滇
    0.06
    Act Density 0.004%

    No Known Activations