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

    Neuronpedia

    INDEX
    Explanations

    say single letter axes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ю
    -0.07
    >>;↵
    -0.07
    Helmet
    -0.07
     $?
    -0.07
     recursion
    -0.07
    _binding
    -0.07
    [*
    -0.06
     jumped
    -0.06
    ;'↵
    -0.06
    !(
    -0.06
    POSITIVE LOGITS
    cret
    0.06
     CONTRIBUT
    0.06
    níkem
    0.06
     گذ
    0.06
     �
    0.06
     refl
    0.06
    ifique
    0.06
    637
    0.06
     exagger
    0.05
     STR
    0.05
    Act Density 0.028%

    No Known Activations