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

    Neuronpedia

    INDEX
    Explanations

    bordered by countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Format
    0.40
     Winter
    0.39
     Spinning
    0.39
     poté
    0.38
     গভীর
    0.38
     かわいい
    0.38
    butadiene
    0.37
    Format
    0.37
     Butterworth
    0.37
     Gem
    0.36
    POSITIVE LOGITS
    籽
    0.38
     ial
    0.37
     appre
    0.35
     ys
    0.35
     __
    0.34
     odb
    0.34
    預
    0.34
    Ns
    0.34
     (__
    0.34
     inline
    0.33
    Act Density 0.005%

    No Known Activations