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

    Neuronpedia

    INDEX
    Explanations

    description or definition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Imperial
    -0.08
    'l
    -0.07
    咳
    -0.07
    Lİ
    -0.07
     PdfP
    -0.07
     Inflate
    -0.07
    .PerformLayout
    -0.07
    联络
    -0.07
    振奋
    -0.07
     Martial
    -0.06
    POSITIVE LOGITS
    XA
    0.07
     Causes
    0.07
    ead
    0.07
    穿
    0.06
    sound
    0.06
    ’une
    0.06
    יופ
    0.06
     proverb
    0.06
    ikes
    0.06
    rikes
    0.06
    Act Density 0.164%

    No Known Activations