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

    Neuronpedia

    INDEX
    Explanations

    language learning platforms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rho
    -0.07
    .charAt
    -0.07
    META
    -0.07
    .Middle
    -0.06
    Thus
    -0.06
    แนว
    -0.06
     Nou
    -0.06
     meme
    -0.06
     �
    -0.06
    bpp
    -0.06
    POSITIVE LOGITS
     steadfast
    0.07
    'article
    0.06
     Units
    0.06
    forder
    0.06
     enhanced
    0.06
    决定
    0.06
     zdraví
    0.06
     Prospect
    0.06
    elopment
    0.06
     decency
    0.06
    Act Density 0.024%

    No Known Activations