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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hobbies
    -0.06
     бол
    -0.06
     ổn
    -0.06
    敬
    -0.06
    ISM
    -0.06
    istem
    -0.06
     CHO
    -0.06
    -index
    -0.06
     suffer
    -0.06
     manos
    -0.06
    POSITIVE LOGITS
    fstream
    0.07
    169
    0.06
    Scoped
    0.06
    (lua
    0.06
     @@
    0.06
     banks
    0.06
    य
    0.06
     Learned
    0.06
    >().
    0.06
    .Native
    0.06
    Act Density 0.000%

    No Known Activations