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

    Neuronpedia

    INDEX
    Explanations

    exclusions from Confidential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bras
    0.48
    c
    0.48
    ca
    0.47
    cin
    0.46
    sc
    0.46
    se
    0.45
    shaders
    0.45
    cn
    0.44
    aterials
    0.44
    D
    0.44
    POSITIVE LOGITS
     által
    0.47
     podmín
    0.45
     Intensity
    0.44
     Emulator
    0.43
     условия
    0.42
     viento
    0.42
     Yamaha
    0.40
     måde
    0.40
     Jamestown
    0.40
     fait
    0.40
    Act Density 0.001%

    No Known Activations