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

    Neuronpedia

    INDEX
    Explanations

    how to use or define

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     And
    0.79
     Especially
    0.77
     Và
    0.73
    那就是
    0.67
     Porque
    0.65
    And
    0.64
     That
    0.63
     İşte
    0.63
     Getting
    0.62
    Especially
    0.62
    POSITIVE LOGITS
     stipulated
    0.76
     originally
    0.75
     customarily
    0.74
     specified
    0.71
    normally
    0.68
     traditionally
    0.67
     conventionally
    0.67
     denoted
    0.66
     typically
    0.65
     kullanılır
    0.65
    Act Density 0.276%

    No Known Activations