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

    Neuronpedia

    INDEX
    Explanations

    surface treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    אוניברס
    -0.07
     superstar
    -0.07
    授课
    -0.07
    ';↵↵
    -0.07
    ᥖ
    -0.07
     Posté
    -0.07
    جزيرة
    -0.06
     Details
    -0.06
     interpreting
    -0.06
    .builders
    -0.06
    POSITIVE LOGITS
    .cmd
    0.08
    mount
    0.07
    cast
    0.07
    _Login
    0.07
    挤
    0.07
     Bry
    0.07
    跻
    0.07
    一团
    0.07
     Destiny
    0.07
    _salary
    0.07
    Act Density 0.046%

    No Known Activations