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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values and function call structures in code

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

    single quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addGap
    -0.75
    addContainerGap
    -0.58
    ágenes
    -0.57
     فريبيس
    -0.55
    -0.52
    andExpect
    -0.50
    ⟬
    -0.50
    انتهای
    -0.47
     CommonModule
    -0.47
    addPreferredGap
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.40
     OMITBAD
    0.38
    Single
    0.36
    single
    0.34
    хьтан
    0.34
     semel
    0.34
    TabStop
    0.33
     Савезне
    0.33
     intptr
    0.33
    protoc
    0.32
    Act Density 0.022%

    No Known Activations