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

    Neuronpedia

    INDEX
    Explanations

    math powers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -reviewed
    -0.09
     schematic
    -0.08
     metast
    -0.08
    ブル
    -0.08
     redesign
    -0.08
     overhaul
    -0.08
     предлага
    -0.08
     redesigned
    -0.08
    Rollback
    -0.07
    Brake
    -0.07
    POSITIVE LOGITS
    IEWS
    0.10
     harmonic
    0.09
     Moments
    0.08
     Noble
    0.08
     நடந்த
    0.08
     hank
    0.08
    ادى
    0.08
     Harm
    0.08
     Getter
    0.08
    ydd
    0.08
    Act Density 0.013%

    No Known Activations