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

    Neuronpedia

    INDEX
    Explanations

    phrases and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soglas
    0.50
    ప్పు
    0.39
    ắng
    0.38
    Ag
    0.36
    arantad
    0.36
    omegranate
    0.36
    薬品
    0.36
     কাব
    0.36
    apuris
    0.36
    ထ
    0.36
    POSITIVE LOGITS
     "=
    0.46
     beset
    0.40
     CFU
    0.39
     kpc
    0.38
     Stoke
    0.38
     marinated
    0.37
     identifica
    0.37
     VP
    0.37
     deploying
    0.37
     sticking
    0.37
    Act Density 0.047%

    No Known Activations