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

    Neuronpedia

    INDEX
    Explanations

    reliability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🐍
    -0.07
     Profit
    -0.07
    iform
    -0.07
    igmatic
    -0.07
    aser
    -0.07
    ổi
    -0.07
    oenix
    -0.07
     bour
    -0.07
    Fox
    -0.06
     BBQ
    -0.06
    POSITIVE LOGITS
     kullanım
    0.08
     behaviours
    0.07
    .Parameter
    0.07
     capability
    0.07
     methods
    0.07
    ᑖ
    0.07
     bottom
    0.07
    鲬
    0.07
    篼
    0.07
    杌
    0.07
    Act Density 0.017%

    No Known Activations