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

    Neuronpedia

    INDEX
    Explanations

    next

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _expect
    -0.07
     accessories
    -0.07
     artists
    -0.07
    emás
    -0.06
     personalities
    -0.06
    ChangeListener
    -0.06
    .upper
    -0.06
     definition
    -0.06
    _contr
    -0.06
    (di
    -0.06
    POSITIVE LOGITS
    UNCT
    0.07
    ص
    0.06
     Lib
    0.06
    مة
    0.06
    志
    0.06
    rish
    0.06
     norske
    0.06
    0.06
    .bit
    0.06
    RO
    0.06
    Act Density 0.028%
    No Known Activations