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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lux
    -0.07
    hdl
    -0.06
    يز
    -0.06
     olmaz
    -0.06
    neck
    -0.06
     trabaj
    -0.06
    _CLI
    -0.06
     desea
    -0.06
    Anim
    -0.06
     bý
    -0.06
    POSITIVE LOGITS
    坊
    0.07
     PROF
    0.06
     Dub
    0.06
    ures
    0.06
    (PHP
    0.06
     Cognitive
    0.06
     UB
    0.06
     ih
    0.06
     คร
    0.06
    _global
    0.06
    Act Density 0.015%

    No Known Activations