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

    Neuronpedia

    INDEX
    Explanations

    console

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subject
    -0.08
    -making
    -0.07
     Weekly
    -0.06
     lidé
    -0.06
     bleibt
    -0.06
    َب
    -0.06
    .body
    -0.06
     �
    -0.06
     Buddh
    -0.06
    [group
    -0.06
    POSITIVE LOGITS
     consoles
    0.08
    .onOptionsItemSelected
    0.07
    swing
    0.07
    Elf
    0.06
    飯店
    0.06
     доз
    0.06
     PartialView
    0.06
    咨
    0.06
     happily
    0.06
    ];
↵
↵
    0.06
    Act Density 0.002%

    No Known Activations