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

    Neuronpedia

    INDEX
    Explanations

    curly brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mac
    -0.06
    も
    -0.06
    phys
    -0.06
     Mac
    -0.06
    _due
    -0.06
    _FOR
    -0.06
     Highly
    -0.06
    _start
    -0.06
    相
    -0.06
     Dub
    -0.06
    POSITIVE LOGITS
     kok
    0.07
    πη
    0.07
    	inst
    0.06
     contractors
    0.06
     thờ
    0.06
    Apply
    0.06
    CPF
    0.06
    Kitchen
    0.06
    ieces
    0.06
     Bureau
    0.06
    Act Density 0.003%

    No Known Activations