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

    Neuronpedia

    INDEX
    Explanations

    options and customization

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’T
    -0.07
    etre
    -0.07
    ová
    -0.07
    ORIZ
    -0.06
    ecided
    -0.06
    novation
    -0.06
    énom
    -0.06
    xcf
    -0.06
     outFile
    -0.06
    emale
    -0.06
    POSITIVE LOGITS
     freely
    0.07
     itemView
    0.06
     anymore
    0.06
     Bu
    0.06
    159
    0.06
    (fill
    0.06
     выше
    0.06
     ∈
    0.06
    (height
    0.06
     CircularProgressIndicator
    0.06
    Act Density 0.034%

    No Known Activations