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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     спів
    -0.07
    _mux
    -0.07
    alizace
    -0.07
    ことに
    -0.06
    .ZERO
    -0.06
     userAgent
    -0.06
    σίας
    -0.06
    .Art
    -0.06
     '>'
    -0.06
     jackets
    -0.06
    POSITIVE LOGITS
     fatty
    0.07
    .Contains
    0.07
     dissip
    0.06
    énom
    0.06
    mar
    0.06
     Them
    0.06
    	Dim
    0.06
    ิร
    0.06
     Nome
    0.06
     classic
    0.06
    Act Density 0.042%

    No Known Activations