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

    Neuronpedia

    INDEX
    Explanations

    Questions and Quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jurors
    -0.07
    Time
    -0.06
     tim
    -0.06
     Time
    -0.06
     focuses
    -0.06
    Times
    -0.06
     Pay
    -0.06
     �
    -0.06
     ej
    -0.06
     Ten
    -0.06
    POSITIVE LOGITS
    (root
    0.07
     activating
    0.07
     hasher
    0.07
    вит
    0.07
    <uint
    0.06
     참가
    0.06
     sah
    0.06
    瓶
    0.06
    _poll
    0.06
     GObject
    0.06
    Act Density 0.019%

    No Known Activations