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

    Neuronpedia

    INDEX
    Explanations

    Housing descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     advocate
    -0.07
     towards
    -0.07
     conservation
    -0.07
    湯
    -0.06
     outf
    -0.06
    ны
    -0.06
     Każ
    -0.06
    atchet
    -0.06
     spent
    -0.06
     errorHandler
    -0.06
    POSITIVE LOGITS
     ListView
    0.08
    鞋子
    0.08
    ascade
    0.07
    黄
    0.07
    .initializeApp
    0.07
    <M
    0.07
     Claw
    0.07
    물
    0.07
    .BigInteger
    0.07
     PLAY
    0.07
    Act Density 0.001%

    No Known Activations