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

    Neuronpedia

    INDEX
    Explanations

    error, status, or user command

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ៤
    0.34
    দিগকে
    0.31
     patitth
    0.31
    <unused2020>
    0.31
    RELATIVA
    0.30
    ४
    0.30
     REACTORS
    0.30
     эффек
    0.30
    ៦
    0.30
    メリット
    0.29
    POSITIVE LOGITS
     you
    0.39
     \
    0.38
     your
    0.36
     requested
    0.36
     the
    0.35
     came
    0.35
    :\
    0.34
    !");
    0.34
    ...");
    0.33
     started
    0.33
    Act Density 0.676%

    No Known Activations