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

    Neuronpedia

    INDEX
    Explanations

    Code and/or negative statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "));
    -0.07
     kvinne
    -0.06
     konci
    -0.06
     đau
    -0.06
    etě
    -0.06
     reste
    -0.06
    aklı
    -0.06
     Cout
    -0.06
    BOVE
    -0.06
    APH
    -0.06
    POSITIVE LOGITS
    である
    0.07
    Document
    0.06
    іш
    0.06
     witches
    0.06
    readcrumb
    0.06
    tags
    0.06
     COMPANY
    0.06
    とい
    0.06
    Concern
    0.06
     ود
    0.06
    Act Density 0.000%

    No Known Activations