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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    杨
    -0.07
    agements
    -0.06
    arı
    -0.06
     guru
    -0.06
     엄
    -0.06
     shining
    -0.06
     Independ
    -0.06
     Ric
    -0.06
     ฟร
    -0.05
    �
    -0.05
    POSITIVE LOGITS
     redesigned
    0.07
     physiological
    0.07
    Edward
    0.07
    .shortcuts
    0.07
     entityId
    0.06
    experiment
    0.06
     decoding
    0.06
     synt
    0.06
    _FRONT
    0.06
     libertin
    0.06
    Act Density 0.000%

    No Known Activations