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

    Neuronpedia

    INDEX
    Explanations

    say "ely" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entrada
    -0.06
     Країна
    -0.06
     �
    -0.06
    @@
    -0.06
    -shirt
    -0.06
     сказала
    -0.06
    raig
    -0.06
     recycl
    -0.06
    ۲۸
    -0.06
     Hä
    -0.05
    POSITIVE LOGITS
     traverse
    0.07
    MAT
    0.07
     UITableViewDelegate
    0.07
    ose
    0.07
    (nav
    0.07
    ze
    0.06
    τό
    0.06
     observe
    0.06
    _win
    0.06
     secure
    0.06
    Act Density 0.001%

    No Known Activations