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

    Neuronpedia

    INDEX
    Explanations

    numerical values in various contexts

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

    UI layout and styling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pozri
    -0.43
     [*]
    -0.38
    EndInit
    -0.38
    return
    -0.36
    Consequently
    -0.36
     Consequently
    -0.35
     Cabrera
    -0.35
     Deshalb
    -0.35
     powst
    -0.35
    Therefore
    -0.34
    POSITIVE LOGITS
    parsedMessage
    0.85
     ujednoznacz
    0.81
    ReusableCell
    0.77
     myſelf
    0.69
     houſe
    0.67
     betweenstory
    0.65
    ParallelGroup
    0.63
     raiſ
    0.61
     ſta
    0.61
     ſte
    0.60
    Act Density 0.005%

    No Known Activations