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

    Neuronpedia

    INDEX
    Explanations

    github action workflow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كافة
    1.05
     கோட்ப
    1.01
    資産
    1.00
    så
    1.00
     Kaleidoscope
    0.97
    ad
    0.96
     spaceShip
    0.95
    ("+
    0.95
     വസ്തു
    0.95
     különböző
    0.93
    POSITIVE LOGITS
    吗
    0.98
    呜
    0.88
     trypt
    0.86
    आज
    0.84
    स्ट
    0.84
     waf
    0.82
     detained
    0.82
     claws
    0.80
    纳入
    0.80
    Err
    0.78
    Act Density 0.013%

    No Known Activations