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

    Neuronpedia

    INDEX
    Explanations

    word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     halde
    -0.07
    z
    -0.07
    ourd
    -0.06
    etheless
    -0.06
     startling
    -0.06
     subclasses
    -0.06
     haystack
    -0.06
    پی
    -0.06
     먼저
    -0.06
    맞
    -0.06
    POSITIVE LOGITS
    unun
    0.07
     Billing
    0.07
    VAS
    0.07
     Clarence
    0.06
    getApplication
    0.06
    revision
    0.06
    风险
    0.06
    RAM
    0.06
     Decoration
    0.06
     prefix
    0.06
    Act Density 0.019%

    No Known Activations