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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SDLK
    -0.07
     शब
    -0.06
     hawk
    -0.06
    бов
    -0.06
    елів
    -0.06
    (lib
    -0.06
    旦
    -0.06
    三三
    -0.06
    mic
    -0.06
    LayoutPanel
    -0.06
    POSITIVE LOGITS
     recognize
    0.07
     Apostle
    0.07
    Modifier
    0.06
    /tools
    0.06
     Nichols
    0.06
    ]))↵
    0.06
    -‐
    0.06
    -length
    0.06
     recognizes
    0.06
     localization
    0.06
    Act Density 0.001%

    No Known Activations