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

    Neuronpedia

    INDEX
    Explanations

    Generic advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrest
    -0.07
    اه
    -0.07
     einz
    -0.07
    さい
    -0.06
    들과
    -0.06
    ارت
    -0.06
    父
    -0.06
    까지
    -0.06
    容易
    -0.06
    Та
    -0.06
    POSITIVE LOGITS
    _prim
    0.06
     Anh
    0.06
    	y
    0.06
    axy
    0.06
    codegen
    0.06
    nen
    0.06
    /editor
    0.06
    icators
    0.06
     enriched
    0.06
     (($
    0.06
    Act Density 0.072%

    No Known Activations