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

    Neuronpedia

    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hoodie
    -0.07
     công
    -0.07
    ��
    -0.07
     décou
    -0.07
     aura
    -0.06
     která
    -0.06
    ział
    -0.06
     масла
    -0.06
     spawns
    -0.06
     uygun
    -0.06
    POSITIVE LOGITS
    igrate
    0.06
     CMS
    0.06
    仓
    0.06
    precation
    0.06
    /dc
    0.06
    (loader
    0.06
    atory
    0.06
    ищ
    0.06
     filesystem
    0.06
    の方
    0.06
    Act Density 0.000%

    No Known Activations