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

    Neuronpedia

    INDEX
    Explanations

    Code non-alphanumeric characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vẻ
    -0.06
    بين
    -0.06
     Fior
    -0.06
     Cle
    -0.06
     Tory
    -0.06
     mạnh
    -0.06
     getaway
    -0.06
    plx
    -0.06
    IMS
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     allev
    0.07
     plug
    0.07
    	MPI
    0.06
     cracks
    0.06
    	strncpy
    0.06
    تبار
    0.06
     Πρω
    0.06
    сию
    0.06
    acak
    0.06
     втра
    0.06
    Act Density 0.005%

    No Known Activations