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

    Neuronpedia

    INDEX
    Explanations

    Arg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icap
    -0.07
    liga
    -0.07
    ancode
    -0.06
    받
    -0.06
    .mapbox
    -0.06
     Jo
    -0.06
    ocator
    -0.06
     Ryzen
    -0.06
    lichen
    -0.06
    ypad
    -0.06
    POSITIVE LOGITS
    _one
    0.07
    ="${
    0.06
    اقل
    0.06
     Timothy
    0.06
     BREAK
    0.06
     besch
    0.06
    ’ét
    0.06
     Nom
    0.06
    (addr
    0.06
    .address
    0.06
    Act Density 0.001%

    No Known Activations