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

    Neuronpedia

    INDEX
    Explanations

    sections of code that involve public and static method definitions

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

    user code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.43
    enderror
    -0.39
    rungsseite
    -0.38
    ContentAlignment
    -0.38
    Personendaten
    -0.37
    قایناقلار
    -0.37
     ujednoznacz
    -0.36
     Jurassic
    -0.36
    PostInfinity
    -0.36
     frem
    -0.36
    POSITIVE LOGITS
    tanleria
    0.63
    expandindo
    0.45
     newVal
    0.44
     CreateTagHelper
    0.42
     ويكيپيديا
    0.41
    İstinadlar
    0.41
     pubblico
    0.40
    Skocz
    0.39
    InitStruct
    0.39
     montanha
    0.38
    Act Density 0.001%

    No Known Activations