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

    Neuronpedia

    INDEX
    Explanations

    differing opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Linear
    -0.07
    ";
↵
    -0.07
    .")
↵
    -0.07
    "){↵
    -0.07
    -sizing
    -0.07
     Technique
    -0.07
    .send
    -0.07
     fulfill
    -0.07
    令
    -0.06
     Questions
    -0.06
    POSITIVE LOGITS
     massac
    0.07
     veg
    0.07
    ael
    0.07
    植被
    0.07
     propriet
    0.07
     hecho
    0.07
     lettre
    0.06
    مة
    0.06
    сот
    0.06
    がかか
    0.06
    Act Density 0.085%

    No Known Activations