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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    routing
    -0.08
     đích
    -0.07
    ária
    -0.07
     seri
    -0.07
     produto
    -0.07
     disob
    -0.06
    .se
    -0.06
    ervation
    -0.06
    ording
    -0.06
     cultivating
    -0.06
    POSITIVE LOGITS
    (runtime
    0.07
    _disable
    0.06
     卡
    0.06
    .TextChanged
    0.06
     Krishna
    0.06
     ukaz
    0.06
     Domin
    0.06
     biç
    0.06
     slideshow
    0.06
     kron
    0.06
    Act Density 0.054%

    No Known Activations