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

    Neuronpedia

    INDEX
    Explanations

    Research-oriented writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Female
    -0.08
     Greens
    -0.07
     Bedroom
    -0.07
    овая
    -0.07
     Platinum
    -0.07
     portraits
    -0.06
     Exposure
    -0.06
     Seek
    -0.06
    판
    -0.06
    _MEMBER
    -0.06
    POSITIVE LOGITS
     twist
    0.07
    ật
    0.07
    CREASE
    0.07
    的兴趣
    0.07
    郄
    0.07
     knack
    0.07
    힛
    0.07
    智能制造
    0.06
    חוז
    0.06
    殃
    0.06
    Act Density 0.088%

    No Known Activations