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

    Neuronpedia

    INDEX
    Explanations

    type names, service names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frequency
    -0.07
     poetry
    -0.07
    。(
    -0.06
     Parsing
    -0.06
    .Count
    -0.06
     Statements
    -0.06
    .Framework
    -0.06
    BuildContext
    -0.06
    ));↵↵
    -0.06
     Slave
    -0.06
    POSITIVE LOGITS
     Theresa
    0.07
     entren
    0.07
     stě
    0.07
     hodin
    0.07
    rarian
    0.07
    xca
    0.06
     backbone
    0.06
    事情
    0.06
    撃
    0.06
    ئة
    0.06
    Act Density 0.004%

    No Known Activations