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

    Neuronpedia

    INDEX
    Explanations

    investigate how or if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     characteristics
    0.62
    characteristics
    0.62
     analyses
    0.55
     economics
    0.54
     studies
    0.54
     분석
    0.51
    analyse
    0.50
     study
    0.50
     analyse
    0.50
    分析
    0.49
    POSITIVE LOGITS
     efecto
    0.45
     hvis
    0.45
     qualquer
    0.43
     effetto
    0.43
    effetto
    0.42
     efeito
    0.40
     Any
    0.40
     whatever
    0.39
     związku
    0.39
     Whatever
    0.39
    Act Density 0.017%

    No Known Activations