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

    Neuronpedia

    INDEX
    Explanations

    pandas dataframe methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ከተ
    0.43
     จง
    0.42
     搭
    0.40
     Row
    0.38
    ⊕
    0.38
    AndUpdate
    0.38
    ุ่ง
    0.38
     इंप
    0.37
     Sind
    0.37
     humiliation
    0.37
    POSITIVE LOGITS
    loc
    0.96
    iloc
    0.91
     loc
    0.87
     Loc
    0.73
     lok
    0.70
    Loc
    0.66
     Lok
    0.62
    LOC
    0.62
    reset
    0.61
     LOC
    0.60
    Act Density 0.025%

    No Known Activations