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

    Neuronpedia

    INDEX
    Explanations

    code-related references and configurations in a programming context

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

    configuration and new things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.61
     AssemblyCompany
    -0.56
     terciopelo
    -0.55
     térmico
    -0.52
     Grüsse
    -0.52
     indígen
    -0.52
     nutricional
    -0.52
     íntimo
    -0.52
     increí
    -0.50
     atardecer
    -0.50
    POSITIVE LOGITS
    enschappelijke
    0.54
     Plu
    0.46
    NgModule
    0.45
     Glo
    0.44
     plu
    0.43
    Wnd
    0.40
    FromArgb
    0.40
     Bul
    0.40
    expandindo
    0.39
    matic
    0.39
    Act Density 0.029%

    No Known Activations