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

    Neuronpedia

    INDEX
    Explanations

    allow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鸣
    -0.31
    é³¥
    -0.28
     Shortcut
    -0.27
    itic
    -0.26
     замеÑĩа
    -0.25
    ADV
    -0.25
     manus
    -0.25
    pickle
    -0.24
     specifying
    -0.24
    被æĬĵ
    -0.24
    POSITIVE LOGITS
     following
    0.29
    éŀł
    0.29
    tant
    0.26
    ttl
    0.26
     TTL
    0.26
    äºĴ
    0.25
    opoulos
    0.25
    imientos
    0.24
    çĽĶ
    0.24
    以ä¸ĭ
    0.24
    Act Density 0.006%

    No Known Activations