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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    であった
    0.53
    Were
    0.50
    学ぶ
    0.49
     comienzan
    0.47
    Required
    0.45
    即可
    0.45
    ってしまう
    0.44
     Were
    0.43
    となっている
    0.43
    しまう
    0.43
    POSITIVE LOGITS
     heard
    0.62
     glimps
    0.56
     learned
    0.54
     spent
    0.52
     messed
    0.51
     ate
    0.51
     caught
    0.50
     did
    0.50
     bought
    0.49
     chased
    0.48
    Act Density 0.145%

    No Known Activations