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

    Neuronpedia

    INDEX
    Explanations

    escape characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [vi
    -0.07
    แค
    -0.07
    colon
    -0.06
    ReceiveProps
    -0.06
     نسبة
    -0.06
    !("
    -0.06
     romant
    -0.06
    �回
    -0.06
    一人
    -0.06
    Freedom
    -0.06
    POSITIVE LOGITS
    /react
    0.07
     README
    0.07
     false
    0.07
     Leave
    0.07
    ,false
    0.06
    SHIP
    0.06
    ώς
    0.06
     concerts
    0.06
     restrict
    0.06
     biased
    0.06
    Act Density 0.021%

    No Known Activations