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

    Neuronpedia

    INDEX
    Explanations

    alternative names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Saudis
    -0.07
    皆
    -0.06
     satellite
    -0.06
     autoload
    -0.06
     tránh
    -0.06
     Encryption
    -0.06
     Package
    -0.06
     hầu
    -0.06
     publishing
    -0.06
    (...)↵
    -0.06
    POSITIVE LOGITS
    tere
    0.07
    .jsx
    0.07
    kept
    0.07
    _depth
    0.07
    boBox
    0.06
    fone
    0.06
     빨
    0.06
     deren
    0.06
    .cmb
    0.06
    VAR
    0.06
    Act Density 0.028%

    No Known Activations