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

    Neuronpedia

    INDEX
    Explanations

    fashioned

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _taxonomy
    -0.07
     그러나
    -0.07
    /general
    -0.07
    .Auth
    -0.07
     estos
    -0.07
    anguages
    -0.06
    /Admin
    -0.06
    Ḵ
    -0.06
    thesized
    -0.06
    艅
    -0.06
    POSITIVE LOGITS
    Increasing
    0.08
     Increasing
    0.08
     WC
    0.07
     BOTTOM
    0.06
    Alarm
    0.06
     diminishing
    0.06
    >(&
    0.06
     mix
    0.06
     Selling
    0.06
     Mostly
    0.06
    Act Density 0.014%

    No Known Activations