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

    Neuronpedia

    INDEX
    Explanations

    citation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     も
    -0.06
    اء
    -0.06
    (mappedBy
    -0.06
     ['.
    -0.06
    .helper
    -0.06
     grads
    -0.06
    `,↵
    -0.06
     geek
    -0.06
     engulf
    -0.05
    ाल
    -0.05
    POSITIVE LOGITS
    arez
    0.07
     Audi
    0.07
     financing
    0.07
     Bihar
    0.07
     McM
    0.07
    cock
    0.06
    -l
    0.06
     ジ
    0.06
    -bodied
    0.06
    https
    0.06
    Act Density 0.000%

    No Known Activations