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

    Neuronpedia

    INDEX
    Explanations

    keys in data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tendency
    0.44
    Trimethyl
    0.44
    bigl
    0.39
     opting
    0.38
    oblastic
    0.38
    heel
    0.37
    Fighting
    0.37
    zigzag
    0.36
     получают
    0.36
     hydroph
    0.36
    POSITIVE LOGITS
     keys
    0.73
     клю
    0.72
    ]['
    0.70
    字段
    0.68
     KEYS
    0.68
    键
    0.68
    keys
    0.66
     KeyError
    0.66
    キー
    0.64
     ключ
    0.63
    Act Density 0.027%

    No Known Activations