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

    Neuronpedia

    INDEX
    Explanations

    high

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IRD
    -0.07
    igDecimal
    -0.07
    ügen
    -0.06
    262
    -0.06
    _dataset
    -0.06
    ůležit
    -0.06
     familia
    -0.06
    ρίζ
    -0.06
     ia
    -0.06
     사업
    -0.06
    POSITIVE LOGITS
     low
    0.08
    _il
    0.06
    billing
    0.06
    �
    0.06
    (""));↵
    0.06
    endency
    0.06
    _long
    0.06
     تک
    0.06
    high
    0.06
    hibited
    0.06
    Act Density 0.004%

    No Known Activations