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

    Neuronpedia

    INDEX
    Explanations

    math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Linear
    -0.08
     PET
    -0.08
    PET
    -0.08
     transmet
    -0.08
     fluores
    -0.07
     FIT
    -0.07
     ceremonia
    -0.07
    …).
    -0.07
     cérémonie
    -0.07
     geöffnet
    -0.07
    POSITIVE LOGITS
     trustworthy
    0.08
     immune
    0.08
     Alias
    0.07
     返回
    0.07
     Sometimes
    0.07
    crib
    0.07
    emake
    0.07
     owner
    0.07
     responsive
    0.07
    cribir
    0.07
    Act Density 0.022%

    No Known Activations