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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating synonyms or alternative names for entities

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

    also known as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LEGGI
    -0.47
    izoen
    -0.44
     nadie
    -0.39
     Libertadores
    -0.38
    Abbiamo
    -0.38
     Moscú
    -0.37
    urysty
    -0.37
    ControllerAdvice
    -0.37
    tighet
    -0.37
    reactstrap
    -0.36
    POSITIVE LOGITS
     known
    0.79
     Known
    0.66
     aka
    0.65
     AKA
    0.63
    known
    0.63
    Known
    0.62
     conhecida
    0.61
     conocido
    0.60
     Aka
    0.59
    Aka
    0.58
    Act Density 0.012%

    No Known Activations