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

    Neuronpedia

    INDEX
    Explanations

    .xlabel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     picking
    -0.07
    *f
    -0.07
     mà
    -0.07
     Private
    -0.07
     failing
    -0.06
     ruining
    -0.06
     пунк
    -0.06
     visto
    -0.06
     mocks
    -0.06
     tp
    -0.06
    POSITIVE LOGITS
    .xlabel
    0.17
    _xlabel
    0.13
     xlabel
    0.09
    xlabel
    0.07
     شرق
    0.06
    closest
    0.06
    imizer
    0.06
    ylabel
    0.06
    afen
    0.06
     flagship
    0.06
    Act Density 0.001%

    No Known Activations