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

    Neuronpedia

    INDEX
    Explanations

    ST

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Push
    -0.07
     Cover
    -0.06
     الطب
    -0.06
    ảnh
    -0.06
    เร
    -0.06
     MainActivity
    -0.06
    vk
    -0.06
    _usage
    -0.06
    273
    -0.06
     À
    -0.05
    POSITIVE LOGITS
                ↵
    0.07
     Bun
    0.07
     weapons
    0.07
     Weapons
    0.07
     Lemma
    0.07
     cleaners
    0.07
                           ↵
    0.07
                              ↵
    0.07
     causes
    0.07
                                 ↵
    0.06
    Act Density 0.000%

    No Known Activations