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

    Neuronpedia

    INDEX
    Explanations

    California universities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "--
    -0.08
     equivalent
    -0.08
    andy
    -0.08
     "
    -0.07
     framed
    -0.07
    缃
    -0.07
     '--
    -0.07
     "%
    -0.07
     의견
    -0.07
    屑
    -0.07
    POSITIVE LOGITS
    _LA
    0.07
     convict
    0.07
    /Input
    0.07
    ᄒ
    0.07
    닯
    0.07
    móvel
    0.07
    _USART
    0.07
    .hover
    0.06
    (filePath
    0.06
     aplik
    0.06
    Act Density 0.003%

    No Known Activations