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

    Neuronpedia

    INDEX
    Explanations

    Research/studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raptors
    -0.06
    -util
    -0.06
     fq
    -0.06
    .sparse
    -0.06
     mnoha
    -0.06
     если
    -0.06
    。この
    -0.06
    NECTION
    -0.06
    تمر
    -0.06
     Glenn
    -0.06
    POSITIVE LOGITS
     vas
    0.08
    (Application
    0.06
     \""
    0.06
    tsx
    0.06
    integr
    0.06
    ovid
    0.06
    );
↵
    0.06
    utas
    0.06
    usi
    0.06
    illusion
    0.06
    Act Density 0.158%

    No Known Activations