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

    Neuronpedia

    INDEX
    Explanations

    opposing viewpoints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offerings
    -0.06
     provinc
    -0.06
    dirs
    -0.06
     advertisements
    -0.06
     bg
    -0.06
     Bad
    -0.06
     ठ
    -0.06
     Hazard
    -0.06
     cassette
    -0.06
    downloads
    -0.06
    POSITIVE LOGITS
     depending
    0.08
     как
    0.07
    validated
    0.06
    foo
    0.06
     Depend
    0.06
    iselect
    0.06
    _SOFT
    0.06
     jejichž
    0.06
    xAE
    0.06
     inspired
    0.06
    Act Density 0.098%

    No Known Activations