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

    Neuronpedia

    INDEX
    Explanations

    acity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rollout
    -0.07
     staining
    -0.06
    llen
    -0.06
    .safe
    -0.06
    .cross
    -0.06
    مانی
    -0.06
     diseño
    -0.06
     Quarry
    -0.06
     Instance
    -0.06
     Wolfe
    -0.06
    POSITIVE LOGITS
    豪
    0.07
    ectar
    0.07
     automotive
    0.07
     exceed
    0.07
     Innov
    0.07
     Inf
    0.07
     $?
    0.06
     NRF
    0.06
    setType
    0.06
    549
    0.06
    Act Density 0.001%

    No Known Activations