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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming concepts and data types

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

    instead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTEX
    -0.75
     iſt
    -0.67
     ſch
    -0.63
     anún
    -0.61
     ſont
    -0.60
     témoig
    -0.59
     queſta
    -0.59
     estekak
    -0.59
     ſta
    -0.59
     verſ
    -0.58
    POSITIVE LOGITS
     instead
    0.52
    EndInit
    0.42
    instead
    0.40
     rather
    0.39
     zamiast
    0.32
     Instead
    0.32
     whereas
    0.32
     вместо
    0.30
    κης
    0.30
    ])).
    0.30
    Act Density 0.051%

    No Known Activations