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

    Neuronpedia

    INDEX
    Explanations

    Tagalog question

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     na
    0.55
     niya
    0.53
     nila
    0.50
     namin
    0.50
     naman
    0.50
     lamang
    0.48
     Moris
    0.44
    ních
    0.44
    ját
    0.43
     umano
    0.43
    POSITIVE LOGITS
    不可以
    0.40
     par
    0.39
     impossible
    0.39
     ores
    0.38
     lettere
    0.38
     parler
    0.38
     Hay
    0.37
     ore
    0.37
     forbid
    0.37
    ew
    0.36
    Act Density 0.001%

    No Known Activations