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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     நீங்கள்
    0.45
    agę
    0.44
     нажмите
    0.43
     pantalla
    0.42
     શકો
    0.42
     Playstation
    0.41
     verhind
    0.40
     gespielt
    0.39
    ोटोरोला
    0.39
    ారో
    0.39
    POSITIVE LOGITS
    OMA
    0.40
    GROUP
    0.38
     pdf
    0.36
    ベ
    0.36
    be
    0.35
    blog
    0.35
     GROUP
    0.35
     hujan
    0.35
    ம
    0.35
    ಮ
    0.35
    Act Density 0.000%

    No Known Activations