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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Please
    -0.08
    Nice
    -0.08
     hardy
    -0.07
    _br
    -0.07
     logically
    -0.07
    Inquiry
    -0.07
    dest
    -0.07
    _orig
    -0.07
     pony
    -0.07
    Bra
    -0.07
    POSITIVE LOGITS
     təhlük
    0.10
     konkur
    0.09
     Überrasch
    0.09
     bede
    0.09
     sorpresa
    0.09
     خطر
    0.08
     epekto
    0.08
     последствия
    0.08
    тыч
    0.08
     Existe
    0.08
    Act Density 0.001%

    No Known Activations