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

    Neuronpedia

    INDEX
    Explanations

    recipes and measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nez
    -0.07
    belongs
    -0.07
     Grand
    -0.07
     großen
    -0.07
    Rose
    -0.07
     Rose
    -0.07
    ihn
    -0.07
    至尊
    -0.07
    灣
    -0.07
    itez
    -0.07
    POSITIVE LOGITS
    _cid
    0.07
    _generation
    0.07
    raisal
    0.07
     المدني
    0.07
    ꡑ
    0.07
    rastructure
    0.07
    往往是
    0.07
     profiling
    0.07
    息息相关
    0.07
     guideline
    0.07
    Act Density 0.005%

    No Known Activations