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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vac
    -0.07
     balance
    -0.07
     meditation
    -0.06
    finite
    -0.06
    _buf
    -0.06
    .vaadin
    -0.06
     decode
    -0.06
     negligent
    -0.06
    Replace
    -0.06
     child
    -0.06
    POSITIVE LOGITS
     yarı
    0.07
    τερη
    0.06
    τές
    0.06
    ;?>↵
    0.06
    wią
    0.06
     trabajar
    0.06
    riba
    0.06
    ıkl
    0.06
    nbsp
    0.06
    picked
    0.06
    Act Density 0.016%

    No Known Activations