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

    Neuronpedia

    INDEX
    Explanations

    emojis and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biasanya
    0.34
    healthy
    0.30
    agenda
    0.29
     Kap
    0.29
     Biasanya
    0.29
    generally
    0.28
     দখলে
    0.28
    usually
    0.28
    azote
    0.28
    resized
    0.28
    POSITIVE LOGITS
     మీద
    0.32
     посредством
    0.32
    또한
    0.31
     από
    0.30
     পুরস্কার
    0.29
    న్
    0.29
     την
    0.29
    媤
    0.28
     සැ
    0.28
     FROM
    0.28
    Act Density 0.000%

    No Known Activations