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

    Neuronpedia

    INDEX
    Explanations

    Scopes and optics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nach
    -0.08
     danach
    -0.08
    iffany
    -0.08
     prose
    -0.07
     בתחום
    -0.07
    ূপ
    -0.07
     Gibt
    -0.07
     Những
    -0.07
    哪些
    -0.07
     thematic
    -0.07
    POSITIVE LOGITS
    hamento
    0.08
    usega
    0.08
     artillery
    0.08
     क्लिक
    0.08
     prayers
    0.08
    laden
    0.08
     Loaded
    0.08
    wait
    0.08
     эта
    0.07
    गढ़
    0.07
    Act Density 0.006%

    No Known Activations