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

    Neuronpedia

    INDEX
    Explanations

    further

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alpha
    -0.07
     Dia
    -0.07
     Queen
    -0.07
     bride
    -0.06
     Narc
    -0.06
    [offset
    -0.06
     pussy
    -0.06
    -letter
    -0.06
    cis
    -0.06
    ẳn
    -0.06
    POSITIVE LOGITS
     further
    0.12
     Further
    0.10
    Further
    0.09
    739
    0.07
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.07
     AuthService
    0.07
     ánh
    0.06
    .flush
    0.06
     офици
    0.06
    orElse
    0.06
    Act Density 0.023%

    No Known Activations