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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Provides
    0.59
    SO
    0.58
     চায়
    0.58
    ")){
    0.57
     pravi
    0.56
    Means
    0.55
     бажа
    0.55
     strikes
    0.55
     recue
    0.55
    MINE
    0.55
    POSITIVE LOGITS
     HX
    0.59
    닛
    0.56
    island
    0.56
    ântul
    0.55
     CM
    0.53
     Erfolg
    0.53
     historii
    0.53
    রাম
    0.53
     Spicy
    0.53
    rH
    0.52
    Act Density 0.000%

    No Known Activations