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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    è·Ŀ离
    -0.27
    PO
    -0.26
    ppo
    -0.26
     orn
    -0.26
     tob
    -0.25
     sat
    -0.25
    esModule
    -0.24
    oping
    -0.24
     yield
    -0.24
     explain
    -0.24
    POSITIVE LOGITS
    uner
    0.31
    åĽłä¸ºæĪij们
    0.29
    æłĭ
    0.29
     __________________↵↵
    0.26
    çĭ¬è§Ĵåħ½
    0.25
    -au
    0.25
    äºļæ´²
    0.25
    dag
    0.25
    frican
    0.25
    客家
    0.25
    Act Density 1.441%

    No Known Activations