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

    Neuronpedia

    INDEX
    Explanations

    planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.86
    7
    0.78
    ﺭ
    0.70
    8
    0.69
    6
    0.68
    .
    0.65
    Ｉ
    0.65
    ile
    0.63
    కు
    0.63
    maker
    0.63
    POSITIVE LOGITS
    q
    1.09
    planning
    1.06
     planning
    1.05
    ul
    1.04
    Planning
    1.02
    ය
    1.00
    ပိုင်း
    0.98
    isinin
    0.96
    ad
    0.95
    л
    0.95
    Act Density 0.003%

    No Known Activations