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

    Neuronpedia

    INDEX
    Explanations

    introducing summary tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     осень
    0.91
    dayspecial
    0.83
     coordinator
    0.73
    raisers
    0.72
    hapsody
    0.72
     cries
    0.71
     популярных
    0.70
    を与
    0.70
     puas
    0.70
     সঞ্জীবনী
    0.69
    POSITIVE LOGITS
     |
    2.08
    |
    1.91
    {|
    1.60
    |"
    1.40
     $|
    1.38
     {|
    1.36
     (|
    1.34
     "|
    1.33
    ｜
    1.33
    }|
    1.33
    Act Density 0.167%

    No Known Activations