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

    Neuronpedia

    INDEX
    Explanations

    Allah, entrances, when, during, ophy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صلاحیت
    0.45
     ASSEMBLY
    0.44
     certifications
    0.44
     દરેક
    0.44
     ہر
    0.44
    IQUE
    0.44
     отвечает
    0.43
     BRIDGE
    0.43
    FindingsResponse
    0.43
    ҉
    0.43
    POSITIVE LOGITS
    treat
    0.51
    tit
    0.50
    protect
    0.47
    config
    0.45
    title
    0.45
    tv
    0.41
    there
    0.41
    admin
    0.41
    heat
    0.41
    tie
    0.40
    Act Density 0.001%

    No Known Activations