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

    Neuronpedia

    INDEX
    Explanations

    references to missing or overlooked elements in various contexts

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

    missing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.76
    SequentialGroup
    -0.60
     CreateTagHelper
    -0.57
    Geplaatst
    -0.57
    bitField
    -0.56
    RectangleBorder
    -0.55
    endpush
    -0.55
    
    -0.54
    TagMode
    -0.52
     Infórmanos
    -0.51
    POSITIVE LOGITS
     rescued
    0.43
     recovering
    0.42
    Missing
    0.40
     Missing
    0.39
     rescue
    0.38
     rescuing
    0.37
     sick
    0.37
     recupero
    0.37
    missing
    0.36
     recovery
    0.35
    Act Density 0.506%

    No Known Activations