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

    Neuronpedia

    INDEX
    Explanations

    language usage discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     месте
    -0.07
     champ
    -0.06
     animation
    -0.06
    关
    -0.06
     grounds
    -0.06
     expert
    -0.06
    느
    -0.06
     operational
    -0.06
    est
    -0.06
    银行
    -0.06
    POSITIVE LOGITS
     Abort
    0.07
    hc
    0.07
    \R
    0.06
    .increment
    0.06
     Tong
    0.06
    plits
    0.06
     %@
    0.06
    .unsubscribe
    0.06
    sic
    0.06
    .VisibleIndex
    0.06
    Act Density 0.137%

    No Known Activations