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

    Neuronpedia

    INDEX
    Explanations

    abstract section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     goats
    0.40
     photographie
    0.38
    aur
    0.38
     hay
    0.38
     aina
    0.37
     надо
    0.37
     квар
    0.37
    vine
    0.37
     następ
    0.36
    adze
    0.36
    POSITIVE LOGITS
     Motivation
    0.55
    Mot
    0.50
    Motivation
    0.50
     Motivational
    0.50
     motivation
    0.48
     abstraction
    0.47
     Mot
    0.46
     motivating
    0.43
     motivates
    0.42
    motivation
    0.42
    Act Density 0.000%

    No Known Activations