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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ４
    -0.07
     střed
    -0.07
     그녀
    -0.07
     elf
    -0.07
     Krishna
    -0.06
     současné
    -0.06
    fstream
    -0.06
    وبی
    -0.06
     lái
    -0.06
    acier
    -0.06
    POSITIVE LOGITS
     messages
    0.07
     recover
    0.06
     implemented
    0.06
    บบ
    0.06
     �
    0.06
    .{
    0.06
     bundled
    0.06
    ungs
    0.06
     affirmation
    0.06
     registr
    0.06
    Act Density 0.003%

    No Known Activations