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
    mob
    -0.07
    раниц
    -0.06
     ترین
    -0.06
    graphs
    -0.06
     طول
    -0.06
    θλη
    -0.06
     конструкции
    -0.06
    comput
    -0.06
    ocê
    -0.06
    приєм
    -0.06
    POSITIVE LOGITS
    buff
    0.07
     ')↵↵
    0.07
     //↵
    0.07
    hdr
    0.07
     wizards
    0.07
    489
    0.07
    _header
    0.06
     [...]↵↵
    0.06
     ')↵
    0.06
    Ž
    0.06
    Act Density 0.000%

    No Known Activations