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

    Neuronpedia

    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     omit
    -0.07
    <stdlib
    -0.06
     blush
    -0.06
    caler
    -0.06
    στη
    -0.06
    isEqual
    -0.06
     chip
    -0.06
     taller
    -0.06
    thinkable
    -0.06
     kn
    -0.06
    POSITIVE LOGITS
     Mısır
    0.07
     muže
    0.07
     Thu
    0.07
    .isLoggedIn
    0.07
     że
    0.07
     että
    0.06
     CHK
    0.06
    777
    0.06
    _DD
    0.06
     Denis
    0.06
    Act Density 0.154%

    No Known Activations