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

    Neuronpedia

    INDEX
    Explanations

    references to foundational components or elements in a theoretical context

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

    building blocks and heavy lifting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emailing
    -0.36
     المعيارى
    -0.35
     fucking
    -0.35
    CharacterOffset
    -0.35
     reais
    -0.34
    merksam
    -0.34
    vertising
    -0.34
    ély
    -0.33
     monthly
    -0.33
     nocturn
    -0.33
    POSITIVE LOGITS
     builders
    0.69
    Build
    0.68
     Build
    0.67
     Builders
    0.67
    builders
    0.66
     build
    0.64
    Builders
    0.63
     costruzione
    0.62
     BUILD
    0.62
    Building
    0.61
    Act Density 0.005%

    No Known Activations