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

    Neuronpedia

    INDEX
    Explanations

    safety and caution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Clearly
    -0.07
     hierarchical
    -0.07
    正常
    -0.07
    elight
    -0.06
    Activities
    -0.06
     alarak
    -0.06
    炮
    -0.06
     yık
    -0.06
    apid
    -0.06
     infographic
    -0.06
    POSITIVE LOGITS
     intermittent
    0.07
     AuthenticationService
    0.07
     instanceof
    0.06
     системи
    0.06
    _Height
    0.06
     mailing
    0.06
    Knowledge
    0.06
     Ansi
    0.06
     Game
    0.06
     tribes
    0.06
    Act Density 0.049%

    No Known Activations