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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sinks
    -0.07
    σμ
    -0.06
     CIS
    -0.06
     sunk
    -0.06
     containers
    -0.06
     fotograf
    -0.06
     Sorry
    -0.06
    .expand
    -0.06
    �
    -0.06
    ank
    -0.06
    POSITIVE LOGITS
    .ERR
    0.07
    genus
    0.07
     próximo
    0.07
    يع
    0.07
    .align
    0.07
    	var
    0.07
     intéress
    0.06
     millennia
    0.06
     Mountain
    0.06
     тяжел
    0.06
    Act Density 0.004%

    No Known Activations