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

    Neuronpedia

    INDEX
    Explanations

    Pronoun followed by verb

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .accuracy
    -0.07
    CHAPTER
    -0.07
    ną
    -0.07
    ่องเท
    -0.06
    jekt
    -0.06
     reveals
    -0.06
    massage
    -0.06
     investigative
    -0.06
     serialize
    -0.06
    .image
    -0.06
    POSITIVE LOGITS
    、『
    0.07
     dispon
    0.07
    -controls
    0.06
    ázd
    0.06
     Pension
    0.06
     repar
    0.06
     prac
    0.06
     bubb
    0.06
    cela
    0.06
    dbcTemplate
    0.06
    Act Density 0.050%

    No Known Activations