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

    Neuronpedia

    INDEX
    Explanations

    software testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tica
    -0.07
    "W
    -0.07
    Various
    -0.07
    Av
    -0.06
     opponents
    -0.06
    .getJSONArray
    -0.06
    Stories
    -0.06
    Else
    -0.06
    	with
    -0.06
     capitals
    -0.06
    POSITIVE LOGITS
     IDR
    0.08
     roční
    0.07
     căn
    0.07
     поряд
    0.06
     vzdál
    0.06
     зрения
    0.06
    看
    0.06
     posicion
    0.06
    (ax
    0.06
    operands
    0.06
    Act Density 0.014%

    No Known Activations