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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (sh
    -0.07
     segments
    -0.07
     кор
    -0.06
    pseudo
    -0.06
    wo
    -0.06
     Vietnamese
    -0.06
     machine
    -0.06
    ama
    -0.06
     preparing
    -0.06
     laundry
    -0.06
    POSITIVE LOGITS
    जर
    0.06
     luaL
    0.06
     lcm
    0.06
    　ﾊ
    0.06
     '..',
    0.06
    ×↵↵
    0.06
     gratuito
    0.06
    ibal
    0.06
    	pl
    0.06
    threat
    0.06
    Act Density 0.251%

    No Known Activations