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

    Neuronpedia

    INDEX
    Explanations

    Light and dark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uang
    -0.07
    (Encoding
    -0.07
     clamp
    -0.07
    theory
    -0.07
    )o
    -0.07
     여
    -0.07
     Marino
    -0.07
     Lose
    -0.07
     heightFor
    -0.06
     Ting
    -0.06
    POSITIVE LOGITS
    ﲰ
    0.08
    azar
    0.07
     marks
    0.07
     Search
    0.07
    /apps
    0.07
    ڍ
    0.07
    "Our
    0.07
     Jaguars
    0.06
    _attention
    0.06
    calling
    0.06
    Act Density 0.008%

    No Known Activations