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

    Neuronpedia

    INDEX
    Explanations

    Frequency response and filters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    analysis
    -0.08
     delito
    -0.08
     sentimental
    -0.08
     entrepreneurship
    -0.07
    MS
    -0.07
     internships
    -0.07
     injury
    -0.07
     entrepreneurial
    -0.07
     delitos
    -0.07
    species
    -0.07
    POSITIVE LOGITS
     gradual
    0.10
     gradually
    0.10
     abruptly
    0.10
     धीरे
    0.10
     резко
    0.10
     अचानक
    0.10
     постепенно
    0.10
     taper
    0.09
     примерно
    0.09
    渐
    0.09
    Act Density 0.006%

    No Known Activations