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

    Neuronpedia

    INDEX
    Explanations

    compile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ية
    -0.07
     jednak
    -0.07
    Host
    -0.07
     ($
    -0.07
    -word
    -0.06
     ont
    -0.06
     headed
    -0.06
    Difficulty
    -0.06
    Hide
    -0.06
    toy
    -0.06
    POSITIVE LOGITS
     onComplete
    0.07
     filtration
    0.07
    kie
    0.07
    ื้
    0.06
     SNAP
    0.06
     prizes
    0.06
    /logging
    0.06
     sağlam
    0.06
     rehears
    0.06
    <C
    0.06
    Act Density 0.009%

    No Known Activations