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

    Neuronpedia

    INDEX
    Explanations

    Code/errors/equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Guid
    -0.07
    peon
    -0.06
    _SYNC
    -0.06
     kterém
    -0.06
    .persist
    -0.06
    __:
    -0.06
    -metal
    -0.06
     yür
    -0.06
     //
↵
    -0.06
    .Serialization
    -0.06
    POSITIVE LOGITS
    ожд
    0.07
    289
    0.07
     HVAC
    0.06
     eylem
    0.06
    Baby
    0.06
    aybe
    0.06
    тин
    0.06
    ケ
    0.06
     engagements
    0.06
    CLU
    0.06
    Act Density 0.000%

    No Known Activations