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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (inflater
    -0.08
    enticator
    -0.07
    AFP
    -0.07
    枋
    -0.07
    edReader
    -0.07
    iens
    -0.07
     JW
    -0.07
    казать
    -0.07
     rotterdam
    -0.07
    Fashion
    -0.07
    POSITIVE LOGITS
     managed
    0.07
    โฆ
    0.06
    โค
    0.06
     antenn
    0.06
    십시
    0.06
    _N
    0.06
    _choice
    0.06
     남
    0.06
    )))↵↵
    0.06
     حاج
    0.06
    Act Density 0.002%

    No Known Activations