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

    Neuronpedia

    INDEX
    Explanations

    Component

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atisf
    -0.07
    oppins
    -0.07
     mitt
    -0.06
     �
    -0.06
    (cin
    -0.06
    (schedule
    -0.06
     oblivious
    -0.06
    /assert
    -0.05
     mins
    -0.05
    imited
    -0.05
    POSITIVE LOGITS
    xAA
    0.08
    Oak
    0.07
    verte
    0.07
    JSON
    0.06
    ErrorMsg
    0.06
    	TRACE
    0.06
    ofire
    0.06
    Project
    0.06
     Phoenix
    0.06
    ует
    0.06
    Act Density 0.002%

    No Known Activations