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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .basicConfig
    -0.08
     Sự
    -0.08
     Fach
    -0.07
    ắc
    -0.07
     Ruf
    -0.07
    Ⓟ
    -0.07
     Vac
    -0.07
     ?>"></
    -0.07
    สาธ
    -0.07
    金沙
    -0.07
    POSITIVE LOGITS
     yi
    0.08
     weight
    0.07
     minutes
    0.07
    感受到
    0.07
    weeks
    0.07
     effects
    0.07
    arges
    0.07
    還要
    0.07
    staking
    0.07
     stopped
    0.06
    Act Density 0.021%

    No Known Activations