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

    Neuronpedia

    INDEX
    Explanations

    ial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enburg
    -0.06
     pioneering
    -0.06
     \$
    -0.06
    OX
    -0.06
    (['/
    -0.06
    _files
    -0.06
    розум
    -0.06
    ORIZED
    -0.06
     deform
    -0.06
     fug
    -0.06
    POSITIVE LOGITS
     może
    0.07
     Globals
    0.07
     dismantle
    0.07
     الخاص
    0.07
    .Promise
    0.07
     norske
    0.06
     druhé
    0.06
    ियर
    0.06
     droit
    0.06
     буду
    0.06
    Act Density 0.000%

    No Known Activations