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

    Neuronpedia

    INDEX
    Explanations

    accurate information and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    őd
    0.42
    Signal
    0.42
    Aus
    0.41
    SRC
    0.41
    Processor
    0.40
    Auf
    0.40
    Input
    0.40
    YN
    0.39
    yn
    0.39
    epsilon
    0.39
    POSITIVE LOGITS
     stretched
    0.44
     liable
    0.43
     accurately
    0.43
     plastered
    0.43
     beaded
    0.42
     pertaining
    0.40
     jis
    0.39
     crowns
    0.39
     birdies
    0.39
     accordingly
    0.39
    Act Density 0.001%

    No Known Activations