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

    Neuronpedia

    INDEX
    Explanations

    code/text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vegan
    -0.07
    _behavior
    -0.06
     Machine
    -0.06
     slime
    -0.06
    "But
    -0.06
    igmat
    -0.06
     OMIT
    -0.06
    glass
    -0.06
    -Time
    -0.06
    +m
    -0.06
    POSITIVE LOGITS
    CANCEL
    0.07
    UpDown
    0.07
     مناسب
    0.06
     sorunu
    0.06
    .classes
    0.06
    (feed
    0.06
     lông
    0.06
     vite
    0.06
    类
    0.06
     臺
    0.06
    Act Density 0.000%

    No Known Activations