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

    Neuronpedia

    INDEX
    Explanations

    activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cruise
    -0.07
    achts
    -0.07
     wanted
    -0.06
     Academic
    -0.06
     Workplace
    -0.06
    XYZ
    -0.06
    Folders
    -0.06
    arı
    -0.06
    Chat
    -0.06
     ↵
    -0.06
    POSITIVE LOGITS
     тех
    0.07
    _EDEFAULT
    0.06
     immutable
    0.06
    .SubElement
    0.06
     PyObject
    0.06
    _IF
    0.06
     dubious
    0.06
    .owl
    0.06
     받아
    0.06
    μήμα
    0.06
    Act Density 0.009%

    No Known Activations