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

    Neuronpedia

    INDEX
    Explanations

    French/Spanish pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crian
    -0.06
     ات
    -0.06
     rng
    -0.06
     contrary
    -0.06
    孝
    -0.06
     cyn
    -0.06
    <s
    -0.06
    manual
    -0.06
    (vec
    -0.06
    -util
    -0.06
    POSITIVE LOGITS
    سة
    0.07
     nghĩ
    0.07
    Gb
    0.07
     Phot
    0.06
     G
    0.06
     us
    0.06
     titleLabel
    0.06
     RK
    0.06
    由
    0.06
    ?("
    0.06
    Act Density 0.012%

    No Known Activations