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

    Neuronpedia

    INDEX
    Explanations

    opposite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (torch
    -0.07
     Expect
    -0.07
    .joda
    -0.06
    ensity
    -0.06
     theatrical
    -0.06
     Density
    -0.06
    opleft
    -0.06
    CO
    -0.06
    /array
    -0.06
    HT
    -0.06
    POSITIVE LOGITS
    Alexander
    0.06
    хран
    0.06
     kurtar
    0.06
    shop
    0.06
    　ヾ
    0.06
    pattern
    0.06
     Jonas
    0.06
    ل
    0.06
     Edmund
    0.06
    cargo
    0.06
    Act Density 0.008%

    No Known Activations