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

    Neuronpedia

    INDEX
    Explanations

    serving size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Caution
    0.39
    पाट
    0.38
     پست
    0.38
    Inside
    0.38
    Luck
    0.38
    ](/
    0.36
    см
    0.36
     १६
    0.36
    Spa
    0.36
     tij
    0.36
    POSITIVE LOGITS
     serving
    0.89
    serving
    0.86
     Serving
    0.82
    Serving
    0.71
     serves
    0.58
     Serv
    0.57
    serve
    0.55
     serve
    0.55
     servings
    0.53
     Serve
    0.50
    Act Density 0.001%

    No Known Activations