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

    Neuronpedia

    INDEX
    Explanations

    playful informal tone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Clear
    0.41
    とにかく
    0.39
     semplicemente
    0.36
     Procedure
    0.36
     чого
    0.36
     అనేది
    0.36
     crucially
    0.36
    Idi
    0.35
     Idi
    0.34
     simply
    0.34
    POSITIVE LOGITS
    ！）
    0.53
    😜
    0.50
    !)
    0.49
     shameless
    0.49
     hehe
    0.47
    !),
    0.46
    !).
    0.45
    ෙක්
    0.45
    してみました
    0.45
     cheeky
    0.45
    Act Density 0.015%

    No Known Activations