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

    Neuronpedia

    INDEX
    Explanations

    expressions of time and context in various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    In [adjective/quantifier]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.62
    .}
    -0.53
     ибо
    -0.52
     because
    -0.52
     porque
    -0.52
     omdat
    -0.51
    %.
    -0.49
     arşivlendi
    -0.48
     ہے۔
    -0.47
    porque
    -0.46
    POSITIVE LOGITS
     inilah
    0.62
    findpost
    0.59
    ंदीखरीदारी
    0.58
    uxxxx
    0.57
    情况下
    0.51
    而言
    0.51
     itulah
    0.49
     inoltre
    0.49
    UnusedPrivate
    0.48
     nutshell
    0.46
    Act Density 0.308%

    No Known Activations