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

    Neuronpedia

    INDEX
    Explanations

    Google account, roster focusing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    合适
    0.55
     През
    0.54
     পেয়ে
    0.53
     Técnica
    0.51
     设计
    0.50
     સમય
    0.48
     Practitioners
    0.47
     ಹಿಂದೆ
    0.47
     Sainsbury
    0.46
    全体
    0.46
    POSITIVE LOGITS
     idiom
    0.71
     oxidation
    0.64
     abrasion
    0.63
     apparatus
    0.59
     spoof
    0.58
     eccentric
    0.55
     mucosal
    0.55
     therein
    0.54
     idios
    0.54
     idi
    0.54
    Act Density 0.000%

    No Known Activations