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

    Neuronpedia

    INDEX
    Explanations

    how it works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     habitudes
    0.46
     guidelines
    0.42
     opciones
    0.42
    hapi
    0.42
     options
    0.41
    Guidelines
    0.41
     possibilidades
    0.40
     ways
    0.39
     contexts
    0.39
    rices
    0.39
    POSITIVE LOGITS
     funzionamento
    1.44
     작동
    1.41
     funcionamento
    1.40
     funcionamiento
    1.36
     fonctionnement
    1.33
    mechanism
    1.21
     mechanism
    1.20
     Mechanism
    1.20
    仕組み
    1.19
    Mechanism
    1.19
    Act Density 0.072%

    No Known Activations