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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    סביר
    -0.07
    SEO
    -0.07
    .pth
    -0.07
    (Parse
    -0.07
    .msg
    -0.06
    prompt
    -0.06
    אלב
    -0.06
     Hairst
    -0.06
    _sold
    -0.06
     sufferers
    -0.06
    POSITIVE LOGITS
    不容
    0.07
    Slide
    0.07
     cush
    0.07
    れない
    0.07
    也没什么
    0.07
     inconsistency
    0.07
     Type
    0.07
     studs
    0.07
     caps
    0.07
    疠
    0.07
    Act Density 0.007%

    No Known Activations