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

    Neuronpedia

    INDEX
    Explanations

    Contractions and prefixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الع
    -0.07
     twist
    -0.07
    ового
    -0.07
     �
    -0.06
    Version
    -0.06
     amps
    -0.06
     luxe
    -0.06
     slope
    -0.06
     lParam
    -0.06
    ystack
    -0.06
    POSITIVE LOGITS
     организации
    0.07
     enters
    0.07
    Ｃ
    0.06
     tank
    0.06
    _pci
    0.06
     Blade
    0.06
     vibrations
    0.06
     repost
    0.06
     sl
    0.06
     Statistical
    0.06
    Act Density 0.058%

    No Known Activations