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

    Neuronpedia

    INDEX
    Explanations

    Tagalog positive adjectives and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ng
    0.71
     ni
    0.69
     adhes
    0.68
     nila
    0.64
     Nf
    0.61
     נא
    0.58
     nc
    0.57
     bukan
    0.57
     जिसने
    0.56
    ectoria
    0.55
    POSITIVE LOGITS
    mam
    0.88
    bib
    0.85
    Mam
    0.80
     pap
    0.78
    bab
    0.75
    tit
    0.74
    abab
    0.74
     Mam
    0.73
    igi
    0.73
    pap
    0.73
    Act Density 0.000%

    No Known Activations