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

    Neuronpedia

    INDEX
    Explanations

    words indicating significance or impact

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

    it makes / means / follows / goes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.66
    脚注の使い方
    -0.66
    TestingModule
    -0.63
    IntoConstraints
    -0.61
    -0.54
     feroit
    -0.54
     auroit
    -0.53
    ंदीखरीदारी
    -0.53
     eût
    -0.53
    érité
    -0.52
    POSITIVE LOGITS
     it
    0.49
     It
    0.49
    它
    0.47
     ins
    0.46
     nó
    0.45
     它
    0.45
    (;;)
    0.41
     Engle
    0.39
     มัน
    0.38
     its
    0.36
    Act Density 0.043%

    No Known Activations