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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     literary
    -0.07
    ・・・↵↵
    -0.07
    חזור
    -0.06
     successful
    -0.06
    (solution
    -0.06
    _dir
    -0.06
    אוקטובר
    -0.06
     professional
    -0.06
     Determin
    -0.06
    ="<?=$
    -0.06
    POSITIVE LOGITS
     البر
    0.08
    /menu
    0.08
    boats
    0.07
    嗍
    0.07
    剥
    0.07
    	be
    0.06
    风味
    0.06
    olumes
    0.06
     smoked
    0.06
    悬浮
    0.06
    Act Density 0.069%

    No Known Activations