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

    Neuronpedia

    INDEX
    Explanations

    Math operations symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilst
    -0.07
    create
    -0.07
     GOLD
    -0.07
    🛤
    -0.07
     exerc
    -0.07
    tam
    -0.07
    .LogWarning
    -0.06
     Xiaomi
    -0.06
    ashion
    -0.06
    ctions
    -0.06
    POSITIVE LOGITS
    唢
    0.07
     hangs
    0.07
    }",
    0.07
     Cocoa
    0.07
    ┤
    0.07
    𝓭
    0.06
     enforce
    0.06
    依靠
    0.06
     highways
    0.06
    -envelope
    0.06
    Act Density 0.031%

    No Known Activations