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

    Neuronpedia

    INDEX
    Explanations

    mathematical formatting structures

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

    end of aligned mathematical block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.68
     ſch
    -0.68
    WithMany
    -0.56
     houſe
    -0.56
     ſy
    -0.55
     ſta
    -0.54
     ſich
    -0.53
     iſt
    -0.53
     verſ
    -0.52
     dafs
    -0.52
    POSITIVE LOGITS
    enumi
    0.48
     defaultstate
    0.45
     مشين
    0.44
    __(/*!
    0.42
     idéia
    0.41
     sekarang
    0.41
     paisagem
    0.40
    GetCurrent
    0.40
    awtextra
    0.40
     needless
    0.39
    Act Density 0.028%

    No Known Activations