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

    Neuronpedia

    INDEX
    Explanations

    ape,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    த்தைப்
    0.35
    琥
    0.35
    Naissance
    0.34
    ធាតុ
    0.33
    콰
    0.33
    For
    0.33
     Columbia
    0.33
    éticas
    0.33
    Columbia
    0.32
    லாக
    0.32
    POSITIVE LOGITS
    الس
    0.42
     Pemer
    0.40
     solder
    0.36
    Middleware
    0.36
    牛奶
    0.36
    中華
    0.36
    藍
    0.36
     الس
    0.35
     Abbas
    0.35
     caves
    0.35
    Act Density 0.007%

    No Known Activations