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

    Neuronpedia

    INDEX
    Explanations

    request

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ственной
    -0.07
    _ll
    -0.07
    Pt
    -0.07
    ﻴ
    -0.07
     UNSIGNED
    -0.06
    .TestCase
    -0.06
    _cats
    -0.06
    mue
    -0.06
     orgas
    -0.06
    Fn
    -0.06
    POSITIVE LOGITS
    قلال
    0.07
    avings
    0.07
    атора
    0.07
     motions
    0.07
     ask
    0.06
    aku
    0.06
     Animation
    0.06
     asked
    0.06
    Batch
    0.06
     demande
    0.06
    Act Density 0.011%

    No Known Activations