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

    Neuronpedia

    INDEX
    Explanations

    period symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ILogger
    -0.07
     dB
    -0.06
     Scala
    -0.06
     plans
    -0.06
     Bec
    -0.06
    _Action
    -0.06
    _EXPECT
    -0.06
     �
    -0.06
     Basement
    -0.06
     UCHAR
    -0.06
    POSITIVE LOGITS
     replica
    0.07
    sorry
    0.07
     Controlled
    0.07
     laptops
    0.07
    стит
    0.07
    roads
    0.07
    Sometimes
    0.07
    ンス
    0.06
     좋
    0.06
     controlled
    0.06
    Act Density 0.021%

    No Known Activations