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

    Neuronpedia

    INDEX
    Explanations

    expected to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ស្ស
    0.82
     memutuskan
    0.78
    戶
    0.75
    czyk
    0.75
     نعرف
    0.75
    ళ్ళు
    0.74
     recognized
    0.72
     Sage
    0.71
    我觉得
    0.71
     지정
    0.71
    POSITIVE LOGITS
    ToBe
    1.22
     fortemente
    1.19
    ly
    1.13
    lly
    0.98
     იყოს
    0.98
    mente
    0.98
     strongly
    0.97
     fortement
    0.96
     להיות
    0.96
     demise
    0.95
    Act Density 0.131%

    No Known Activations