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

    Neuronpedia

    INDEX
    Explanations

    align

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Position
    -0.08
     UUID
    -0.07
    Lo
    -0.07
    .Nome
    -0.07
     sĩ
    -0.06
    ega
    -0.06
    Namespace
    -0.06
    _store
    -0.06
    DATE
    -0.06
    ｰ
    -0.06
    POSITIVE LOGITS
     volcan
    0.08
    ちゃん
    0.07
     ген
    0.06
     ":
    0.06
     маст
    0.06
     줄
    0.06
     April
    0.06
     illumin
    0.06
     �
    0.06
     büy
    0.06
    Act Density 0.002%

    No Known Activations