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

    Neuronpedia

    INDEX
    Explanations

    Utilitarianism maximize happiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ভ্রমণের
    0.54
    াবলীর
    0.48
    WriteStream
    0.47
     Waterproof
    0.45
    ポケモン
    0.45
     CGRectMake
    0.44
     uczniów
    0.44
     ແມ່ນ
    0.43
    тной
    0.43
     elevates
    0.43
    POSITIVE LOGITS
    isas
    0.48
    ações
    0.45
    ANGO
    0.44
    iret
    0.44
    isa
    0.43
    avec
    0.43
    s
    0.43
    ]
    0.43
     Les
    0.42
    ``
    0.42
    Act Density 0.006%

    No Known Activations