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

    Neuronpedia

    INDEX
    Explanations

    explaining hypothetical situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ede
    0.44
    ers
    0.44
    der
    0.43
     just
    0.43
    ach
    0.41
    在
    0.41
    lands
    0.41
    less
    0.40
    Land
    0.40
    aber
    0.40
    POSITIVE LOGITS
    ទំនាក់
    0.58
     動画
    0.53
    拍攝
    0.51
     plufieurs
    0.51
    ੦
    0.50
    alakip
    0.50
    📹
    0.49
    🍲
    0.49
    ഭവ
    0.47
     \\..
    0.47
    Act Density 0.007%

    No Known Activations