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

    Neuronpedia

    INDEX
    Explanations

    takes care of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ong
    0.88
    re
    0.80
    bagian
    0.80
    OID
    0.79
    to
    0.75
     plusieurs
    0.73
     amass
    0.72
    isBlank
    0.72
    ק
    0.72
    umā
    0.71
    POSITIVE LOGITS
     políticos
    0.86
     notícias
    0.82
     públicos
    0.80
     관련
    0.78
    вших
    0.78
     países
    0.77
     GIFs
    0.77
     مز
    0.76
     chilli
    0.76
     Mej
    0.76
    Act Density 0.000%

    No Known Activations