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

    Neuronpedia

    INDEX
    Explanations

    say "visa"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.07
    ByteArray
    -0.06
     Anthem
    -0.06
    侯
    -0.06
    Bond
    -0.06
     bond
    -0.06
     backyard
    -0.06
    ">(
    -0.06
    анта
    -0.06
     Therefore
    -0.06
    POSITIVE LOGITS
     hits
    0.07
    (sys
    0.07
    _waiting
    0.07
     inse
    0.07
     každé
    0.07
    Intro
    0.06
     simult
    0.06
     hit
    0.06
     filt
    0.06
     primer
    0.06
    Act Density 0.012%

    No Known Activations