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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "]=="
    -0.07
    409
    -0.07
    $c
    -0.07
    tables
    -0.07
    HeaderView
    -0.06
    216
    -0.06
     '"'
    -0.06
    »)
    -0.06
    ','%
    -0.06
    .False
    -0.06
    POSITIVE LOGITS
     rootNode
    0.06
     slee
    0.06
    にお
    0.06
    胡
    0.06
     feudal
    0.06
     elé
    0.06
     �
    0.06
    яет
    0.06
    死
    0.06
     잔
    0.06
    Act Density 0.260%

    No Known Activations