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

    Neuronpedia

    INDEX
    Explanations

    Progress reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cruc
    -0.07
     asthma
    -0.06
    .range
    -0.06
    otypes
    -0.06
    (eq
    -0.06
     reader
    -0.06
    cakes
    -0.06
    _imp
    -0.06
    ��态
    -0.06
    Army
    -0.06
    POSITIVE LOGITS
    entionPolicy
    0.07
    ebilir
    0.07
     basın
    0.07
     προσ
    0.06
    чин
    0.06
    DivElement
    0.06
     cursed
    0.06
    感じ
    0.06
     chí
    0.06
    .Arguments
    0.06
    Act Density 0.223%

    No Known Activations