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

    Neuronpedia

    INDEX
    Explanations

    random

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <A
    -0.07
    .datas
    -0.07
    NameValuePair
    -0.07
     �
    -0.07
     comerc
    -0.07
    '=>'
    -0.07
    填补
    -0.06
    	font
    -0.06
     contacts
    -0.06
    辛辣
    -0.06
    POSITIVE LOGITS
    reshold
    0.08
    Challenge
    0.07
    isplay
    0.07
    셢
    0.07
    ENCH
    0.07
    ossa
    0.07
    Maybe
    0.07
    اوية
    0.07
    (group
    0.07
    Coordinates
    0.07
    Act Density 0.004%

    No Known Activations