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

    Neuronpedia

    INDEX
    Explanations

    equal signs and assignment statements in code

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

    SQL availability queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.96
     propOrder
    -0.78
    DispatchToProps
    -0.74
    aarrggbb
    -0.72
     pleaſure
    -0.72
     uLocal
    -0.71
     esternos
    -0.70
    Personendaten
    -0.70
     ſche
    -0.70
     ſind
    -0.69
    POSITIVE LOGITS
    oil
    0.33
    =
    0.32
     very
    0.31
     babak
    0.31
    Oil
    0.30
     Tiere
    0.30
     Oil
    0.29
     vieles
    0.28
    mp
    0.28
    `
    0.28
    Act Density 0.187%

    No Known Activations