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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Irr
    -0.08
     Fortsch
    -0.08
     당시
    -0.08
     Toledo
    -0.08
     Parsing
    -0.07
    Nearby
    -0.07
     Barg
    -0.07
    ithmetic
    -0.07
    (grammar
    -0.07
     Häuser
    -0.07
    POSITIVE LOGITS
     preferably
    0.11
    尺寸
    0.10
     ideally
    0.09
     recommendations
    0.09
     standards
    0.09
     Canva
    0.08
     accommodating
    0.08
     желательно
    0.08
     recommended
    0.08
    Adobe
    0.08
    Act Density 0.007%

    No Known Activations