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

    Neuronpedia

    INDEX
    Explanations

    Large or small quantities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Document
    -0.07
    unds
    -0.07
    .AddItem
    -0.07
     Salon
    -0.07
    Naming
    -0.07
    Clazz
    -0.06
    orses
    -0.06
    Hyper
    -0.06
     Bis
    -0.06
    <Player
    -0.06
    POSITIVE LOGITS
    七
    0.07
     ovarian
    0.06
     Pear
    0.06
     relatives
    0.06
    ...",↵
    0.06
     lower
    0.06
     बज
    0.06
    まり
    0.06
    !.↵↵
    0.06
     thật
    0.06
    Act Density 0.037%

    No Known Activations