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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LANE
    -0.08
    ╦
    -0.07
     $("#
    -0.07
    قب
    -0.07
     במסגרת
    -0.06
     PATCH
    -0.06
    _collect
    -0.06
     ומת
    -0.06
     bryster
    -0.06
     State
    -0.06
    POSITIVE LOGITS
    	product
    0.08
    long
    0.07
    Array
    0.07
    Productos
    0.07
     iw
    0.07
     leveled
    0.07
    ᯙ
    0.07
     menor
    0.07
    difference
    0.07
     sigma
    0.07
    Act Density 0.015%

    No Known Activations