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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .mj
    -0.07
     ],
↵
    -0.06
    悲
    -0.06
     Academ
    -0.06
     Rope
    -0.06
     sonic
    -0.06
     Presbyterian
    -0.06
     fueron
    -0.06
    ROUGH
    -0.06
     NSError
    -0.06
    POSITIVE LOGITS
     qualify
    0.08
    cheduled
    0.07
    ANDING
    0.07
    DateString
    0.07
    Case
    0.06
    seconds
    0.06
    XC
    0.06
    Integration
    0.06
     ca
    0.06
    ¯Â
    0.06
    Act Density 0.003%

    No Known Activations