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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nikdo
    -0.07
    Opera
    -0.06
     Older
    -0.06
    美国
    -0.06
     Bắc
    -0.06
    pwd
    -0.06
    Ja
    -0.06
     Mature
    -0.06
    ımlar
    -0.06
    iamo
    -0.06
    POSITIVE LOGITS
    _san
    0.07
    .Assign
    0.07
     decking
    0.06
    ται
    0.06
     mf
    0.06
    ังก
    0.06
     ignore
    0.06
     budou
    0.06
     må
    0.06
    ẳng
    0.06
    Act Density 0.060%

    No Known Activations