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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (def
    -0.07
    DTO
    -0.06
     Vim
    -0.06
    -Pro
    -0.06
     funnel
    -0.06
     Některá
    -0.06
    _RB
    -0.06
     eliminated
    -0.05
     Stoke
    -0.05
     доб
    -0.05
    POSITIVE LOGITS
    PRECATED
    0.08
     війни
    0.07
     университ
    0.07
     agosto
    0.06
     Integrity
    0.06
    That
    0.06
     başar
    0.06
     utiliza
    0.06
    listening
    0.06
    HeaderText
    0.06
    Act Density 0.001%

    No Known Activations