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

    Neuronpedia

    INDEX
    Explanations

    Fujitsu

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     folds
    -0.07
     underst
    -0.07
    (weight
    -0.06
    _metadata
    -0.06
    elligence
    -0.06
     david
    -0.06
    ogi
    -0.06
    itors
    -0.06
     sights
    -0.06
     женщин
    -0.06
    POSITIVE LOGITS
     mue
    0.07
    imbledon
    0.07
     kanal
    0.06
    SG
    0.06
    _IOCTL
    0.06
     لها
    0.06
     puberty
    0.06
     JAN
    0.06
     adb
    0.06
     �
    0.06
    Act Density 0.022%

    No Known Activations