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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ukes
    -0.06
     compartir
    -0.06
     gig
    -0.06
    _standard
    -0.06
     lavor
    -0.06
     teen
    -0.06
    .IsFalse
    -0.06
     recourse
    -0.06
    Elapsed
    -0.06
    董事
    -0.06
    POSITIVE LOGITS
     trăm
    0.08
     Bluetooth
    0.07
    ей
    0.07
    lee
    0.07
    [E
    0.06
    ंग
    0.06
    [F
    0.06
     батар
    0.06
     наб
    0.06
    ми
    0.06
    Act Density 0.013%

    No Known Activations