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

    Neuronpedia

    INDEX
    Explanations

    Gives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     różnych
    -0.06
     wäre
    -0.06
    videos
    -0.06
    =.
    -0.06
    �
    -0.06
     warnings
    -0.06
    ubby
    -0.06
     monot
    -0.06
    Framebuffer
    -0.06
    :"#
    -0.06
    POSITIVE LOGITS
    .SQLite
    0.08
     flesh
    0.07
     lifespan
    0.07
    ⇖
    0.07
     ula
    0.07
     GN
    0.07
    解放
    0.07
    侍
    0.07
    _place
    0.07
     Citadel
    0.07
    Act Density 0.113%

    No Known Activations