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
     Coch
    -0.07
    bounding
    -0.07
    						
↵
    -0.06
    familia
    -0.06
    _PICTURE
    -0.06
     Gesture
    -0.06
    амет
    -0.06
     Gordon
    -0.06
    printf
    -0.06
     Abyss
    -0.06
    POSITIVE LOGITS
     heiß
    0.06
    高等
    0.06
     bodies
    0.06
     cheat
    0.06
     hommes
    0.06
     유
    0.06
     kingdom
    0.06
    	background
    0.06
     нужно
    0.06
     Παρ
    0.06
    Act Density 0.010%

    No Known Activations