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

    Neuronpedia

    INDEX
    Explanations

    website domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ef
    0.42
    expl
    0.39
     This
    0.38
    sor
    0.38
     。,
    0.38
     .
    0.38
    ini
    0.37
    ison
    0.37
    inn
    0.37
    utt
    0.37
    POSITIVE LOGITS
    שית
    0.43
     কতক
    0.39
     overse
    0.39
    म
    0.39
     sulit
    0.38
    ประชา
    0.38
     grate
    0.38
    лює
    0.38
     orchestras
    0.38
    তিপ
    0.37
    Act Density 0.001%

    No Known Activations