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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wind
    -0.08
    gens
    -0.08
     tender
    -0.07
     Phys
    -0.07
    	ans
    -0.07
    温度
    -0.07
    긴
    -0.07
    ts
    -0.07
    =pd
    -0.07
    광
    -0.07
    POSITIVE LOGITS
    ママ
    0.07
    ﮡ
    0.07
    UILDER
    0.07
    込め
    0.07
     SHARE
    0.06
    ATRIX
    0.06
     decreasing
    0.06
    _mE
    0.06
    Calls
    0.06
     ASIC
    0.06
    Act Density 0.428%

    No Known Activations