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

    Neuronpedia

    INDEX
    Explanations

    take or whisper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fire
    0.56
    UN
    0.55
    ALL
    0.52
    Fire
    0.51
    FIRE
    0.51
    Search
    0.47
    Authors
    0.47
    숲
    0.47
    MAN
    0.46
    Like
    0.46
    POSITIVE LOGITS
     Automotive
    0.47
     xhrObj
    0.46
     cau
    0.45
    ంప
    0.45
     ceded
    0.45
     prije
    0.45
     intención
    0.44
     belangrijkste
    0.44
     ausges
    0.43
     relinquished
    0.43
    Act Density 0.001%

    No Known Activations