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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ero
    -0.07
    rze
    -0.07
    anno
    -0.07
    beros
    -0.06
     Jesse
    -0.06
    ワイト
    -0.06
    _HEAD
    -0.06
     Bristol
    -0.06
     Bangalore
    -0.06
    친
    -0.06
    POSITIVE LOGITS
    _media
    0.07
     pedals
    0.06
    Parameters
    0.06
     Scalars
    0.06
    ']>;↵
    0.06
    里
    0.06
     encore
    0.06
     основных
    0.06
     glitches
    0.06
     grav
    0.06
    Act Density 0.017%

    No Known Activations