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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tender
    -0.07
    aram
    -0.07
    PropTypes
    -0.07
    \:
    -0.07
    :.
    -0.07
     vegetable
    -0.06
    .notes
    -0.06
    gressor
    -0.06
     MPG
    -0.06
     прав
    -0.06
    POSITIVE LOGITS
    уль
    0.07
     Asset
    0.06
    bron
    0.06
    DOMNode
    0.06
    νι
    0.06
    _logging
    0.06
     завд
    0.06
     ul
    0.06
    كون
    0.06
     #%
    0.06
    Act Density 0.042%

    No Known Activations