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

    Neuronpedia

    INDEX
    Explanations

    breakdown and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    合适
    0.51
     Técnica
    0.49
     পেয়ে
    0.48
     मद्देनजर
    0.46
    欅
    0.46
     केरल
    0.46
     идут
    0.45
     ಹಿಂದೆ
    0.45
     સમય
    0.44
     леген
    0.44
    POSITIVE LOGITS
     oxidation
    0.56
     idiom
    0.54
     abrasion
    0.53
     oxidase
    0.47
     oscillation
    0.47
     therein
    0.46
     exagger
    0.46
     parody
    0.45
     spoof
    0.45
     {
    0.45
    Act Density 5.071%

    No Known Activations