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

    Neuronpedia

    INDEX
    Explanations

    statements related to official declarations and attributions of statements

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

    statements or assertions

    np_acts-logits-general · gemini-2.0-flash

    reported statements and observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.84
     ComVisible
    -0.67
     rospy
    -0.66
     quæ
    -0.61
     uſe
    -0.61
    withIdentifier
    -0.58
    ükemmel
    -0.57
     Monfieur
    -0.57
     Majefty
    -0.57
     themſelves
    -0.56
    POSITIVE LOGITS
    SourceChecksum
    0.64
     noting
    0.63
     concern
    0.58
    :"
    0.57
     dizendo
    0.57
    álva
    0.57
     pihaknya
    0.56
    Intial
    0.56
     faptul
    0.56
     concerns
    0.55
    Act Density 0.248%

    No Known Activations