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

    Neuronpedia

    INDEX
    Explanations

    programming-related terminology and concepts

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

    foreign language names and searches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.88
     AssemblyCompany
    -0.56
    Obrázky
    -0.51
     TestBed
    -0.50
    DockStyle
    -0.48
    MouseAdapter
    -0.47
    VolleyError
    -0.47
    Personendaten
    -0.47
    PullParser
    -0.45
     Mise
    -0.44
    POSITIVE LOGITS
     Rueda
    0.43
     Schall
    0.42
     Kalt
    0.40
     Neuk
    0.40
     Heilig
    0.39
     defaultstate
    0.39
    ępo
    0.39
     Stroh
    0.39
     Segel
    0.38
    effetto
    0.38
    Act Density 0.038%

    No Known Activations