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

    Neuronpedia

    INDEX
    Explanations

    references to specific types of models and toys used in construction or play

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

    toy models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     orilla
    -0.44
     ANCHE
    -0.44
     vigencia
    -0.44
    JoinTable
    -0.44
     normalidad
    -0.42
     xuyên
    -0.41
     generación
    -0.40
     śmier
    -0.40
     Welle
    -0.40
     visibilidad
    -0.39
    POSITIVE LOGITS
     toy
    0.68
     Toy
    0.64
    toy
    0.63
    Toy
    0.62
     miniature
    0.61
     miniatures
    0.60
    miniature
    0.58
     modell
    0.55
     miniatura
    0.55
     toys
    0.55
    Act Density 0.011%

    No Known Activations