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
     creed
    -0.08
     standout
    -0.07
     Indies
    -0.06
     Initiative
    -0.06
     Handling
    -0.06
     Giant
    -0.06
     sind
    -0.06
     decide
    -0.06
    IBM
    -0.06
     shaky
    -0.06
    POSITIVE LOGITS
     플레이
    0.07
    ,:,:
    0.06
    GameData
    0.06
     должна
    0.06
    _WORD
    0.06
    .offset
    0.06
    )value
    0.06
     msg
    0.06
     δικ
    0.06
    .ceil
    0.06
    Act Density 0.003%

    No Known Activations