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

    Neuronpedia

    INDEX
    Explanations

    problems and solutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Horny
    -0.07
    home
    -0.06
    bearing
    -0.06
    846
    -0.06
    위원
    -0.06
    KY
    -0.06
    ANDROID
    -0.06
    homes
    -0.06
    shipping
    -0.06
    ,eg
    -0.06
    POSITIVE LOGITS
     siguiente
    0.07
    融
    0.07
     lj
    0.07
    <usize
    0.07
    ,var
    0.06
    >;↵↵
    0.06
     Odin
    0.06
     ribbon
    0.06
    урн
    0.06
     Era
    0.06
    Act Density 0.108%

    No Known Activations