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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deliber
    -0.06
    Black
    -0.06
    )x
    -0.06
    _'.$
    -0.06
     Dann
    -0.06
     handleMessage
    -0.06
    ModelProperty
    -0.06
    ालय
    -0.06
    ocard
    -0.06
    -election
    -0.06
    POSITIVE LOGITS
    .Pe
    0.07
    slope
    0.07
     redu
    0.06
    typed
    0.06
    Magn
    0.06
    ु
    0.06
     exerc
    0.06
     �
    0.06
    锦
    0.06
     negligible
    0.06
    Act Density 0.065%

    No Known Activations