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

    Neuronpedia

    INDEX
    Explanations

    quantities and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    兩種
    0.24
     parts
    0.24
     components
    0.23
     componenti
    0.23
     componentes
    0.23
    デル
    0.22
     části
    0.22
     partes
    0.22
    两种
    0.22
     étape
    0.22
    POSITIVE LOGITS
     dozen
    0.39
    dozen
    0.34
     दर्जन
    0.30
     шт
    0.29
    개의
    0.29
     additional
    0.29
     examples
    0.28
     solcher
    0.28
     જેટ
    0.27
    additional
    0.27
    Act Density 0.096%

    No Known Activations