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

    Neuronpedia

    INDEX
    Explanations

    about ¾ of a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Voz
    0.44
    pozy
    0.37
    सेप्ट
    0.37
    Ꮥ
    0.37
     ওয়
    0.37
    uais
    0.36
    ᔨ
    0.36
    драв
    0.36
    শিয়া
    0.36
    ર્ગ
    0.36
    POSITIVE LOGITS
     ¾
    0.57
    ¾
    0.45
     leo
    0.42
     bugs
    0.41
     ½
    0.40
     Leo
    0.38
     piles
    0.38
     quell
    0.38
     Choices
    0.38
     ይመ
    0.38
    Act Density 0.003%

    No Known Activations