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

    Neuronpedia

    INDEX
    Explanations

    able, ible, cible suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    า
    0.70
     a
    0.68
    та
    0.63
    il
    0.59
    া
    0.59
     Beyoncé
    0.55
     Treated
    0.54
    ට්
    0.53
     A
    0.52
     Infantry
    0.52
    POSITIVE LOGITS
    IT
    0.59
    ка
    0.57
    ও
    0.56
    AT
    0.54
    AK
    0.53
    も
    0.52
    OM
    0.52
    ết
    0.51
    ID
    0.49
    EN
    0.48
    Act Density 0.000%

    No Known Activations