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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Material
    -0.07
    �
    -0.07
    按钮
    -0.07
    另
    -0.07
    oused
    -0.07
    -</
    -0.06
     Holder
    -0.06
     tuo
    -0.06
     ко
    -0.06
     nộp
    -0.06
    POSITIVE LOGITS
    startswith
    0.06
    št
    0.06
     donations
    0.06
    ntl
    0.06
    (xhr
    0.06
    itr
    0.06
    -validator
    0.06
    ')){↵
    0.06
     Surv
    0.06
     Baths
    0.06
    Act Density 0.049%

    No Known Activations