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

    Neuronpedia

    INDEX
    Explanations

    doctype

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blames
    -0.06
     Sav
    -0.06
     remodeling
    -0.06
     puts
    -0.06
     cré
    -0.06
     Claims
    -0.06
    Client
    -0.05
     Sh
    -0.05
    맥
    -0.05
     Noticed
    -0.05
    POSITIVE LOGITS
    )에
    0.07
    awei
    0.07
    ategori
    0.06
    igrate
    0.06
     tribal
    0.06
    ��
    0.06
    .Profile
    0.06
    ा�
    0.06
    runtime
    0.06
    meler
    0.06
    Act Density 0.000%

    No Known Activations