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

    Neuronpedia

    INDEX
    Explanations

    say "second letter is p/h"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doctoral
    -0.09
     educating
    -0.08
    指甲
    -0.07
     الكبرى
    -0.07
    Third
    -0.07
    伋
    -0.07
     trillion
    -0.07
     Garcia
    -0.07
     verte
    -0.07
    公顷
    -0.07
    POSITIVE LOGITS
     kä
    0.08
    —to
    0.07
    環境
    0.07
    (to
    0.07
    >((
    0.07
    مواق
    0.07
     cycl
    0.07
     solver
    0.07
    ﯦ
    0.07
     DataGridView
    0.07
    Act Density 0.005%

    No Known Activations