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

    Neuronpedia

    INDEX
    Explanations

    Checking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     روان
    -0.08
     �
    -0.08
    -called
    -0.08
     aspirations
    -0.08
    bie
    -0.08
    alue
    -0.07
    IUM
    -0.07
     الإلكتروني
    -0.07
     willingly
    -0.07
     پری
    -0.07
    POSITIVE LOGITS
     apakah
    0.10
     налич
    0.09
    一下
    0.09
    ว่
    0.08
    是否
    0.08
    Against
    0.08
     isempty
    0.08
     gest
    0.08
     isset
    0.08
     дали
    0.08
    Act Density 0.013%

    No Known Activations