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

    Neuronpedia

    INDEX
    Explanations

    blocks of code and programming structures

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

    German, programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    -0.36
    InputBorder
    -0.35
     relâche
    -0.35
    RectangleBorder
    -0.35
    ban
    -0.34
    MessageTagHelper
    -0.34
     ban
    -0.32
    pyx
    -0.32
     
    -0.32
    TestingModule
    -0.31
    POSITIVE LOGITS
    rungsseite
    0.86
     Verſ
    0.74
     ſont
    0.68
     laſſen
    0.68
     ſta
    0.66
     müſſen
    0.64
     ujednoznacz
    0.63
     Houſe
    0.62
     dieſer
    0.62
     Anſ
    0.61
    Act Density 0.016%

    No Known Activations