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

    Neuronpedia

    INDEX
    Explanations

    quantity or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     عمل
    0.84
     voidaan
    0.76
    榭
    0.75
    ponin
    0.73
    मेन
    0.73
     dục
    0.73
     marathon
    0.73
     ponen
    0.72
     möchten
    0.72
     වෙත
    0.72
    POSITIVE LOGITS
    ভ
    0.79
     tanto
    0.74
    ホテル
    0.73
    hell
    0.71
    igious
    0.69
    ემ
    0.67
    उ
    0.66
    ↥
    0.66
     Sta
    0.65
    ینه
    0.65
    Act Density 0.000%

    No Known Activations