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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المالية
    -0.07
    isateur
    -0.07
    Nonnull
    -0.07
    娠
    -0.07
     liegt
    -0.07
     African
    -0.07
     Washington
    -0.07
    annabin
    -0.07
    =N
    -0.07
    \Url
    -0.07
    POSITIVE LOGITS
     careers
    0.06
    𝒆
    0.06
     друг
    0.06
     appl
    0.06
    𝒔
    0.06
    plr
    0.06
    pipeline
    0.06
    ই
    0.06
     właś
    0.06
     II
    0.06
    Act Density 0.071%

    No Known Activations