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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amentos
    -0.07
     تور
    -0.06
     asynchronous
    -0.06
    isors
    -0.06
     ISC
    -0.06
     precarious
    -0.06
    client
    -0.06
    �
    -0.06
    .Pattern
    -0.06
    jobs
    -0.06
    POSITIVE LOGITS
     Clarkson
    0.07
    emm
    0.07
     Ав
    0.07
    ('',
    0.07
    -known
    0.06
    (New
    0.06
     posed
    0.06
     реп
    0.06
    ob
    0.06
    :function
    0.06
    Act Density 0.033%

    No Known Activations