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

    Neuronpedia

    INDEX
    Explanations

    Loyalty Programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    1.03
    CE
    0.97
    r
    0.97
    c
    0.95
    t
    0.95
    滲
    0.88
    ке
    0.88
    v
    0.88
    displays
    0.86
    s
    0.85
    POSITIVE LOGITS
     Meskipun
    1.01
    ۂ
    0.89
     genug
    0.89
     !***
    0.88
     Харків
    0.87
     Abbiamo
    0.86
    ہوں
    0.86
    ンドウ
    0.85
     今天
    0.84
     Begriffe
    0.84
    Act Density 0.000%

    No Known Activations