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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asia
    -0.07
    uent
    -0.07
    ò
    -0.07
    umu
    -0.06
    .err
    -0.06
     şimdi
    -0.06
    flowers
    -0.06
    ::::::::::::::::
    -0.06
    uš
    -0.06
     landfill
    -0.06
    POSITIVE LOGITS
    ∨
    0.06
     geniş
    0.06
     JAVA
    0.06
     mantra
    0.06
    نویس
    0.06
     privileges
    0.06
    /fwlink
    0.06
    kaar
    0.06
     eylem
    0.06
     Eğer
    0.06
    Act Density 0.010%

    No Known Activations