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

    Neuronpedia

    INDEX
    Explanations

    bulleted lists and uses of the word "wouldn't" or "weren't"

    oai_token-act-pair · gemini-2.0-flash

    Technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NUMX
    -0.88
     Efq
    -0.64
     doubtnut
    -0.57
    ſelves
    -0.56
    ^(@)
    -0.55
     myſelf
    -0.50
    ".
    -0.47
    ſelf
    -0.47
     leaſt
    -0.47
    ."*
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    0.66
    Geplaatst
    0.65
     recevrez
    0.64
    ⓧ
    0.62
    Tell
    0.59
     graines
    0.59
     fumée
    0.59
     continúas
    0.58
     dég
    0.58
     kasarigan
    0.57
    Act Density 7.837%

    No Known Activations