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

    Neuronpedia

    INDEX
    Explanations

    capacity planning and building

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    える
    1.19
    ance
    1.03
    afar
    1.03
    ುತ್ತವೆ
    0.91
    ድግዳ
    0.91
    ма
    0.88
    akers
    0.88
    ام
    0.87
    ков
    0.87
     wayside
    0.87
    POSITIVE LOGITS
     for
    1.64
    ר
    1.42
    2
    1.40
    ur
    1.36
    on
    1.35
    5
    1.34
    m
    1.33
    7
    1.33
     Capacity
    1.32
    for
    1.29
    Act Density 0.010%

    No Known Activations