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

    Neuronpedia

    INDEX
    Explanations

    object properties and configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    差距
    0.38
     shock
    0.33
     Alo
    0.32
     overall
    0.32
     great
    0.31
     pride
    0.31
    勾
    0.31
     distinction
    0.30
     ak
    0.30
    yyyy
    0.30
    POSITIVE LOGITS
     [`
    0.46
    :["
    0.45
     niets
    0.44
    ：「
    0.44
    ['-
    0.42
    ":[{"
    0.41
    :"))
    0.41
     ["[
    0.41
     repart
    0.40
     Оюн
    0.40
    Act Density 0.007%

    No Known Activations