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

    Neuronpedia

    INDEX
    Explanations

    Code settings/preferences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kp
    -0.07
    (vm
    -0.07
    950
    -0.07
    lycer
    -0.07
     Error
    -0.07
     Watches
    -0.06
     ctypes
    -0.06
     Download
    -0.06
    _sphere
    -0.06
     kwargs
    -0.06
    POSITIVE LOGITS
    �
    0.06
     mev
    0.06
     adjunct
    0.06
    removeAttr
    0.06
     الات
    0.06
    .addTo
    0.06
     downgrade
    0.06
    _general
    0.06
    .filtered
    0.06
    _ITEMS
    0.06
    Act Density 0.027%

    No Known Activations