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

    Neuronpedia

    INDEX
    Explanations

    specific letters representing variables in a structured format

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

    cur: 0x7b

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سكانية
    -0.49
     препратки
    -0.48
     NSCoder
    -0.47
     kaarangay
    -0.43
     PeEnEo
    -0.41
    Хьажоргаш
    -0.41
    InSection
    -0.41
    rungsseite
    -0.40
    needs
    -0.40
     ochrony
    -0.39
    POSITIVE LOGITS
     ſte
    0.51
     SwitchCompat
    0.49
     Aufstieg
    0.47
     userSchema
    0.46
    mpotent
    0.46
    Wage
    0.46
     uLocal
    0.45
     useState
    0.44
     laſt
    0.44
     INSTANCE
    0.44
    Act Density 0.016%

    No Known Activations