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

    Neuronpedia

    INDEX
    Explanations

    C++ template code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endeavour
    -0.07
    ประเภท
    -0.07
    ousedown
    -0.07
    .timeline
    -0.07
     Komm
    -0.07
     продолж
    -0.07
     od
    -0.07
    BTTag
    -0.07
     starting
    -0.07
     Anth
    -0.07
    POSITIVE LOGITS
    hare
    0.07
     staples
    0.07
    (stop
    0.07
    },{↵
    0.07
    installer
    0.07
    larını
    0.07
    awl
    0.06
    방
    0.06
    䃎
    0.06
    /Framework
    0.06
    Act Density 0.001%

    No Known Activations