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

    Neuronpedia

    INDEX
    Explanations

    numbers or ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     હતી
    0.68
     Ее
    0.68
     cevap
    0.67
     செயல்
    0.65
    FontFace
    0.65
     برانيه
    0.65
     गोपनीयता
    0.65
     лица
    0.64
     yanıt
    0.64
    月から
    0.63
    POSITIVE LOGITS
    ish
    2.86
     ish
    2.50
    ISH
    2.13
    odd
    1.76
    ishly
    1.71
    something
    1.69
     odd
    1.62
     something
    1.56
    plus
    1.52
    Something
    1.43
    Act Density 0.501%

    No Known Activations