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

    Neuronpedia

    INDEX
    Explanations

    Code and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mue
    -0.06
     ам
    -0.06
     Popup
    -0.06
     principally
    -0.06
    یر
    -0.06
    ymes
    -0.06
     झ
    -0.06
     Pir
    -0.06
     SpaceX
    -0.06
    Structure
    -0.06
    POSITIVE LOGITS
     그냥
    0.07
    Когда
    0.07
     stdout
    0.07
    /ne
    0.07
     Boat
    0.07
    ользоват
    0.07
    imm
    0.07
    Helmet
    0.07
     Voice
    0.06
    setChecked
    0.06
    Act Density 0.000%

    No Known Activations