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

    Neuronpedia

    INDEX
    Explanations

    estimated metrics and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ROT
    0.74
    Pow
    0.72
    Agg
    0.71
    Concrete
    0.69
    Aut
    0.69
    Un
    0.68
    indexOf
    0.67
    Cursor
    0.65
    ल्
    0.65
    Command
    0.64
    POSITIVE LOGITS
     warfare
    1.09
     matters
    1.09
     minded
    1.04
    ……..
    1.04
    …..
    1.02
     ofte
    1.02
    …….
    1.02
    …………..
    1.01
    ……….
    1.01
     ideologies
    1.01
    Act Density 0.842%

    No Known Activations