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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .innerHTML
    -0.08
    Aaron
    -0.07
     arguably
    -0.07
    wishlist
    -0.06
    опрос
    -0.06
    uarios
    -0.06
    .relu
    -0.06
     Lyrics
    -0.06
     subtle
    -0.06
    铺
    -0.06
    POSITIVE LOGITS
     Dynam
    0.07
     constructing
    0.07
     boots
    0.07
    aviolet
    0.07
     PN
    0.07
     injecting
    0.06
    contra
    0.06
     Reasons
    0.06
    apeutic
    0.06
     stroll
    0.06
    Act Density 0.000%

    No Known Activations