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

    Neuronpedia

    INDEX
    Explanations

    Checking for existence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Virgin
    -0.09
    asque
    -0.08
     solv
    -0.08
     Zee
    -0.08
     Moon
    -0.08
     Thu
    -0.08
     temporary
    -0.08
     Tung
    -0.08
     ons
    -0.08
     Xing
    -0.07
    POSITIVE LOGITS
     whereby
    0.09
    Reached
    0.08
     regarding
    0.08
    oinen
    0.08
    oby
    0.08
     המב
    0.08
    _ASSERT
    0.08
    (()
    0.08
    ُ
    0.08
     意
    0.08
    Act Density 0.003%

    No Known Activations