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

    Neuronpedia

    INDEX
    Explanations

    say "Share/Related post"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    止
    -0.07
    放
    -0.07
    恐慌
    -0.07
     mathematics
    -0.07
    数字货币
    -0.07
    られ
    -0.07
    .dx
    -0.07
    从业
    -0.07
    揣
    -0.07
    춥
    -0.07
    POSITIVE LOGITS
    xAB
    0.07
     Rede
    0.07
     shred
    0.07
     Property
    0.07
    ப
    0.07
    (eventName
    0.06
     swinger
    0.06
     Manson
    0.06
     eve
    0.06
     implying
    0.06
    Act Density 0.000%

    No Known Activations