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

    Neuronpedia

    INDEX
    Explanations

    newest [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saudável
    1.24
    𝙊
    1.22
    𝗜
    1.20
    ùi
    1.13
    ள்
    1.13
    认为
    1.13
    }$
    1.12
     chắn
    1.11
     способности
    1.07
    IBLE
    1.05
    POSITIVE LOGITS
    d
    1.73
    с
    1.60
    ac
    1.37
    em
    1.37
    ু
    1.34
    u
    1.34
    b
    1.34
    a
    1.33
    ing
    1.30
    ed
    1.29
    Act Density 0.001%

    No Known Activations