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

    Neuronpedia

    INDEX
    Explanations

    tool

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    1.61
     encir
    1.53
    મ
    1.43
     Clouds
    1.36
    ς
    1.36
    𝙙
    1.36
    ())));
    1.34
    ſt
    1.34
     Deshalb
    1.33
    г
    1.33
    POSITIVE LOGITS
     matemático
    2.36
     doméstica
    2.30
     instrumento
    2.03
     dinâmica
    2.02
    ۹
    1.97
     líquido
    1.93
     técnico
    1.92
     mecanismo
    1.92
     herramienta
    1.91
     mecánico
    1.91
    Act Density 0.241%

    No Known Activations