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

    Neuronpedia

    INDEX
    Explanations

    neither nor else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vs
    0.48
    vs
    0.44
    FS
    0.41
    但是在
    0.39
    ВС
    0.38
    effectuer
    0.38
    Ε
    0.38
    iris
    0.38
    ifi
    0.37
     एस
    0.37
    POSITIVE LOGITS
     Neither
    0.61
     কিংবা
    0.56
    Neither
    0.56
     neither
    0.55
     Nor
    0.54
     Nope
    0.50
    那种
    0.48
     aquela
    0.47
     nor
    0.46
    那
    0.46
    Act Density 0.098%

    No Known Activations