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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a reference to a specific file or component within a larger framework

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

    part of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.53
     itinéraires
    -0.46
    +#+#
    -0.40
    makeConstraints
    -0.39
     kaarangay
    -0.38
    ंदीखरीदारी
    -0.37
     дописавши
    -0.36
    SourceChecksum
    -0.36
     ролях
    -0.35
     contigo
    -0.35
    POSITIVE LOGITS
     część
    0.67
     parte
    0.66
     onderdeel
    0.65
     část
    0.63
     part
    0.63
     PARTE
    0.59
     części
    0.57
     bagian
    0.57
     часть
    0.56
    parte
    0.55
    Act Density 0.020%

    No Known Activations