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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bonds
    -0.06
     Their
    -0.06
     corr
    -0.06
     blast
    -0.06
    irmingham
    -0.06
     bạc
    -0.06
     sinks
    -0.06
     बन
    -0.06
    杂
    -0.06
     티
    -0.06
    POSITIVE LOGITS
     citations
    0.07
     systematic
    0.07
    ーチ
    0.07
    なん
    0.07
    .getContext
    0.06
    featured
    0.06
    ######
    0.06
    =""/>↵
    0.06
     noreferrer
    0.06
    스코
    0.06
    Act Density 0.021%

    No Known Activations