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

    Neuronpedia

    INDEX
    Explanations

    physical form or fluid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sequest
    0.39
     στους
    0.39
    orf
    0.37
    ляє
    0.35
     ফ্যাস
    0.35
    矶
    0.34
     ariel
    0.34
     and
    0.33
     Sext
    0.33
     amino
    0.33
    POSITIVE LOGITS
    ukar
    0.43
    nueva
    0.42
    evol
    0.40
    Dictionaries
    0.40
    THR
    0.39
    |");
    0.38
    Tomato
    0.38
    MP
    0.38
    <unused26>
    0.38
     తెర
    0.38
    Act Density 0.000%

    No Known Activations