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

    Neuronpedia

    INDEX
    Explanations

    words following "solid"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    も
    0.42
    众
    0.42
    ेक्षित
    0.39
    疠
    0.39
    वेदनशील
    0.38
    ैस
    0.38
    憫
    0.38
    ยอม
    0.37
    시
    0.37
    neze
    0.37
    POSITIVE LOGITS
    Solid
    1.12
     solid
    1.09
     Solid
    1.04
    solid
    0.97
     solidify
    0.87
    SOLID
    0.82
     sólido
    0.80
     SOLID
    0.80
    固
    0.80
    ifying
    0.79
    Act Density 0.012%

    No Known Activations