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

    Neuronpedia

    INDEX
    Explanations

    frustration or frustrated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    べき
    1.74
    ン
    1.59
    เป็น
    1.58
    きた
    1.58
    1.53
    ας
    1.52
    一些
    1.45
    很多
    1.42
    স্থলে
    1.36
    ct
    1.35
    POSITIVE LOGITS
    да
    1.95
     científ
    1.72
    दायक
    1.61
    MENTS
    1.59
    ھ
    1.59
    ҷи
    1.51
    त्रेयी
    1.50
    Ꮐ
    1.48
     DMSO
    1.46
    ParaName
    1.46
    Act Density 0.020%

    No Known Activations