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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pen
    -0.08
     pesticides
    -0.08
     words
    -0.07
    _pet
    -0.07
     underline
    -0.07
     lines
    -0.07
     Henry
    -0.07
    Group
    -0.07
    _styles
    -0.07
    Dist
    -0.07
    POSITIVE LOGITS
    asier
    0.07
    oppers
    0.07
    OLER
    0.07
    탉
    0.07
     roaring
    0.07
    ANTITY
    0.07
    州区
    0.07
    넉
    0.07
    אוניב
    0.07
    。，
    0.06
    Act Density 0.001%

    No Known Activations