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

    Neuronpedia

    INDEX
    Explanations

    picking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Beta
    -0.07
     cigarettes
    -0.06
     anak
    -0.06
    ecome
    -0.06
    riger
    -0.06
    훅
    -0.06
     declining
    -0.06
    meteor
    -0.06
     Citation
    -0.06
    怔
    -0.06
    POSITIVE LOGITS
     bonuses
    0.08
    感兴趣
    0.07
    	check
    0.07
     handheld
    0.07
    iminal
    0.06
     Match
    0.06
     conta
    0.06
     handleMessage
    0.06
     Domino
    0.06
     جديد
    0.06
    Act Density 0.001%

    No Known Activations