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

    Neuronpedia

    INDEX
    Explanations

    disambiguation and choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     améli
    0.44
     mejorar
    0.43
     bolje
    0.43
     migliorare
    0.43
    GROW
    0.41
     قادر
    0.40
     améliorer
    0.40
     আপনার
    0.39
    improve
    0.39
     sinh
    0.39
    POSITIVE LOGITS
     crossroads
    0.60
     options
    0.50
     redirect
    0.49
     Alternatives
    0.47
     endpoints
    0.46
     lists
    0.46
     junctions
    0.46
     două
    0.45
     choices
    0.44
     redirection
    0.44
    Act Density 0.004%

    No Known Activations