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

    Neuronpedia

    INDEX
    Explanations

    say "pt/px"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Congress
    -0.07
    一个是
    -0.07
     useSelector
    -0.07
    iktig
    -0.07
     Jeg
    -0.07
     Congress
    -0.07
    hover
    -0.07
    hound
    -0.07
     Eve
    -0.07
    dup
    -0.06
    POSITIVE LOGITS
     signed
    0.07
     prepare
    0.07
    爆款
    0.07
     LO
    0.07
     saf
    0.07
    安定
    0.07
    AILABLE
    0.07
    /not
    0.06
    扩张
    0.06
    正品
    0.06
    Act Density 0.000%

    No Known Activations