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

    Neuronpedia

    INDEX
    Explanations

    specific numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xb
    0.36
    í
    0.34
    pecific
    0.33
    iple
    0.33
    enen
    0.33
    ites
    0.32
    oft
    0.32
    ib
    0.32
    ined
    0.32
     negra
    0.32
    POSITIVE LOGITS
    ཝ
    0.43
     如果
    0.42
     abelian
    0.39
    如果
    0.39
     ಅಧಿಕ
    0.38
     Fitbit
    0.38
     Referring
    0.38
     sourceL
    0.38
    ងឺ
    0.38
     Navbar
    0.37
    Act Density 0.018%

    No Known Activations