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

    Neuronpedia

    INDEX
    Explanations

    magazine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᅠ
    -0.07
    inth
    -0.07
    hour
    -0.07
     симв
    -0.07
    .NAME
    -0.06
    .ImageLayout
    -0.06
     cats
    -0.06
    ණ
    -0.06
    snd
    -0.06
    第三届
    -0.06
    POSITIVE LOGITS
    🈲
    0.07
    ⵛ
    0.07
    采集
    0.07
     Legion
    0.07
    .deck
    0.07
     disposal
    0.06
    횔
    0.06
     malaria
    0.06
    蓂
    0.06
    pected
    0.06
    Act Density 0.003%

    No Known Activations