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

    Neuronpedia

    INDEX
    Explanations

    negation phrases or symbols that indicate conditions are not met

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

    ! followed by dependency or storage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.55
     GenerationType
    -0.54
    Alexandria
    -0.50
     InputDecoration
    -0.49
     houſe
    -0.49
    TextHelper
    -0.48
     Alexandria
    -0.48
     vandens
    -0.46
    pernicus
    -0.46
    bkz
    -0.44
    POSITIVE LOGITS
    (!
    1.05
     (!
    0.85
    (!$
    0.65
     {!
    0.63
     (!$
    0.59
     !_
    0.55
    {!
    0.55
    (!__
    0.54
    (!_
    0.54
     (!_
    0.52
    Act Density 0.004%

    No Known Activations