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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ælland
    -0.07
     Bracket
    -0.07
    STRACT
    -0.07
    _DEFIN
    -0.06
     fue
    -0.06
    <Token
    -0.06
    &utm
    -0.06
     přid
    -0.06
    _CANNOT
    -0.06
    (control
    -0.06
    POSITIVE LOGITS
    abyte
    0.07
    救
    0.07
    _workflow
    0.06
     TV
    0.06
    inte
    0.06
    APER
    0.06
     Multi
    0.06
     حمل
    0.06
    .readFile
    0.06
    кар
    0.06
    Act Density 0.014%

    No Known Activations