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

    Neuronpedia

    INDEX
    Explanations

    website domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     `>=
    0.65
    მასრულ
    0.63
     長袖
    0.61
    🤧
    0.59
     Immunohist
    0.59
    Caracter
    0.59
    DefineConstants
    0.57
     intracellular
    0.57
     دشمن
    0.57
    DOCTYPE
    0.56
    POSITIVE LOGITS
    com
    1.04
     website
    0.95
     com
    0.94
    website
    0.92
     net
    0.82
    info
    0.81
    webs
    0.79
     Com
    0.79
    Website
    0.78
    farm
    0.76
    Act Density 0.004%

    No Known Activations