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

    Neuronpedia

    INDEX
    Explanations

    terms related to empirical research and empirical evidence

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

    words starting with "Emp"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Noten
    -0.50
    XmlAccessorType
    -0.50
    rzez
    -0.50
    /**
    -0.49
    unser
    -0.47
    akei
    -0.45
    MLLoader
    -0.45
     Suiza
    -0.44
     Rückseite
    -0.44
     ακόμα
    -0.44
    POSITIVE LOGITS
     emp
    2.13
     Emp
    2.09
    Emp
    1.91
    emp
    1.69
     EMP
    1.68
    EMP
    1.45
     Empathy
    1.04
     Empress
    1.02
     Kemp
    1.00
     empathy
    1.00
    Act Density 0.005%

    No Known Activations