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

    Neuronpedia

    INDEX
    Explanations

    You can find information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ylle
    0.82
    Pre
    0.75
    pre
    0.73
    Ti
    0.67
    CHES
    0.66
    groupBox
    0.65
    Arche
    0.63
     چیر
    0.63
    ರೀ
    0.63
    Preg
    0.63
    POSITIVE LOGITS
     city
    0.72
     retracted
    0.67
     arcade
    0.65
     sustainable
    0.65
     vill
    0.64
     down
    0.64
     feu
    0.63
    aji
    0.63
     折
    0.62
    peau
    0.62
    Act Density 0.002%

    No Known Activations