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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INF
    -0.08
    غر
    -0.07
     mềm
    -0.07
    bil
    -0.07
    TU
    -0.07
    centroid
    -0.07
    �
    -0.07
     Helena
    -0.07
    ANTI
    -0.07
     त
    -0.06
    POSITIVE LOGITS
     CrossAxisAlignment
    0.06
    (gameObject
    0.06
    }")↵↵
    0.06
     examining
    0.06
    .authService
    0.06
    ,data
    0.06
    	audio
    0.06
     @_;↵↵
    0.05
    !")↵↵
    0.05
    rending
    0.05
    Act Density 0.257%

    No Known Activations