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

    Neuronpedia

    INDEX
    Explanations

    exploring villages, watch faces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    也不是
    0.50
    History
    0.49
    Those
    0.48
     announce
    0.48
    Odd
    0.47
    였
    0.47
     bukanlah
    0.46
    eksi
    0.46
     odd
    0.45
     acid
    0.45
    POSITIVE LOGITS
    ത്
    0.51
    ாட்டு
    0.48
     Mohammed
    0.47
    াশ
    0.47
    hill
    0.47
    ettha
    0.46
     yüksek
    0.46
     ලබා
    0.46
    ту
    0.45
     путем
    0.45
    Act Density 0.000%

    No Known Activations