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

    Neuronpedia

    INDEX
    Explanations

    Representation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    fik
    -0.07
    'id
    -0.06
    效果
    -0.06
     foundational
    -0.06
     dů
    -0.06
    lol
    -0.06
    _RA
    -0.06
     DESIGN
    -0.06
     acordo
    -0.06
    POSITIVE LOGITS
     take
    0.07
     tý
    0.07
     خان
    0.06
    '''↵↵
    0.06
     practically
    0.06
    での
    0.06
    elling
    0.06
    .NEW
    0.06
    ]*
    0.06
     eagerly
    0.06
    Act Density 0.001%

    No Known Activations