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

    Neuronpedia

    INDEX
    Explanations

    references to game mechanics and stats

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

    network parameters and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.84
     Chwiliwch
    -0.79
     تضيفلها
    -0.79
    Datuak
    -0.73
    Portail
    -0.72
    évaluateur
    -0.70
    MessageOf
    -0.68
    IUrlHelper
    -0.66
     насељу
    -0.66
    makeConstraints
    -0.65
    POSITIVE LOGITS
     loss
    0.43
    Loss
    0.35
     Loss
    0.34
     pertes
    0.31
    Reducer
    0.31
     menac
    0.30
     losses
    0.29
     dwindling
    0.28
     udara
    0.28
    warning
    0.27
    Act Density 0.008%

    No Known Activations