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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pedag
    -0.10
    ronter
    -0.09
     شا
    -0.08
     pleasantly
    -0.08
     randint
    -0.08
     tällä
    -0.08
    .randint
    -0.08
    THANK
    -0.08
     랜
    -0.08
     ಪೊ
    -0.08
    POSITIVE LOGITS
     plaintiffs
    0.15
     alleged
    0.15
     defendants
    0.14
     alleging
    0.14
     alleges
    0.14
     plaintiff
    0.13
     suing
    0.12
     sued
    0.12
     defendant
    0.12
     Plaint
    0.12
    Act Density 0.154%

    No Known Activations