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

    Neuronpedia

    INDEX
    Explanations

    Math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    уз
    -0.07
    oph
    -0.07
     fifteen
    -0.07
    -mounted
    -0.06
    fg
    -0.06
     win
    -0.06
    _ru
    -0.06
     $↵↵
    -0.06
    sharing
    -0.06
    Match
    -0.06
    POSITIVE LOGITS
     breadcrumb
    0.08
     выгляд
    0.07
    补
    0.07
     Druid
    0.07
    例如
    0.07
     обеспеч
    0.06
     geri
    0.06
     забезпеч
    0.06
     bleibt
    0.06
    (ti
    0.06
    Act Density 0.004%

    No Known Activations