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

    Neuronpedia

    INDEX
    Explanations

    inheritance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тер
    -0.07
    .Scene
    -0.07
    ิโล
    -0.06
    	   ↵
    -0.06
    _EXPI
    -0.06
     Mum
    -0.06
     Tir
    -0.06
     depicts
    -0.06
    陵
    -0.06
    Spin
    -0.06
    POSITIVE LOGITS
     Eva
    0.06
     overturned
    0.06
     unwanted
    0.06
    urchased
    0.06
    lle
    0.06
    emodel
    0.06
    кид
    0.06
    alsex
    0.06
    emap
    0.06
    怀
    0.06
    Act Density 0.020%

    No Known Activations