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

    Neuronpedia

    INDEX
    Explanations

    association

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stabilize
    -0.07
     Respond
    -0.07
     Thick
    -0.07
     stabilized
    -0.07
     Cell
    -0.07
     Inspired
    -0.06
    良
    -0.06
     electroly
    -0.06
     Tro
    -0.06
    Color
    -0.06
    POSITIVE LOGITS
    ีข
    0.06
     unconventional
    0.06
    ])(
    0.06
     sexuales
    0.06
     orgy
    0.06
    (span
    0.06
    enticated
    0.06
    utorial
    0.06
    recio
    0.06
     tranquil
    0.06
    Act Density 0.027%

    No Known Activations