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

    Neuronpedia

    INDEX
    Explanations

    phrases describing clarity and simplicity in processes or concepts

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

    straightforward approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auroit
    -0.59
     cáps
    -0.54
     Inscrivez
    -0.52
     imprimée
    -0.51
     صوتيه
    -0.50
    pecabe
    -0.50
     Taktlose
    -0.49
     recargable
    -0.49
    attoos
    -0.48
     Wikimedijinoj
    -0.48
    POSITIVE LOGITS
     straightforward
    0.88
     uncomplicated
    0.65
    easy
    0.56
    躇
    0.53
    oward
    0.52
     easy
    0.52
    0.51
     approach
    0.51
    pensive
    0.50
     routine
    0.50
    Act Density 0.007%

    No Known Activations