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

    Neuronpedia

    INDEX
    Explanations

    step

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鸢
    -0.29
    acon
    -0.28
    orda
    -0.27
     chÃło
    -0.27
    plr
    -0.27
    eczy
    -0.26
    èIJĿ
    -0.26
    elli
    -0.26
    _overlap
    -0.25
    elsen
    -0.25
    POSITIVE LOGITS
    为äºĨ让
    0.30
    ickle
    0.27
    å¾Ģä¸ĭ
    0.26
    è¡į
    0.26
    对ä»ĸ
    0.25
    对她
    0.25
    ستاÙĨ
    0.25
    çĽ´è¾¾
    0.24
     derivation
    0.24
    çİij
    0.24
    Act Density 0.381%

    No Known Activations