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

    Neuronpedia

    INDEX
    Explanations

    situations and experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >M
    -0.07
     sánh
    -0.07
    alom
    -0.07
    /--
    -0.06
    -s
    -0.06
     prostit
    -0.06
     рах
    -0.06
     PARTIC
    -0.06
     neighbor
    -0.06
     saber
    -0.06
    POSITIVE LOGITS
    软
    0.07
    _permalink
    0.07
     Kunden
    0.06
    Requires
    0.06
     Ngb
    0.06
    prix
    0.06
    (doc
    0.06
     Heat
    0.06
    势
    0.06
     uzun
    0.06
    Act Density 0.305%

    No Known Activations