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

    Neuronpedia

    INDEX
    Explanations

    gone and done confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uzzi
    0.76
     liter
    0.75
     heavily
    0.71
     medi
    0.71
     AD
    0.71
     Hers
    0.70
     azar
    0.69
     comm
    0.69
    landır
    0.68
    مین
    0.67
    POSITIVE LOGITS
    ებით
    0.84
     besuchen
    0.84
    uanya
    0.83
     podido
    0.83
    פל
    0.82
    वैसे
    0.82
     supernat
    0.80
    釣り
    0.79
    ამდე
    0.79
    布置
    0.78
    Act Density 0.005%

    No Known Activations