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

    Neuronpedia

    INDEX
    Explanations

    file contents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mod
    -0.07
    ChangeListener
    -0.06
     additions
    -0.06
     rated
    -0.06
     highly
    -0.06
    437
    -0.06
    cean
    -0.06
    aries
    -0.06
     bound
    -0.06
     short
    -0.06
    POSITIVE LOGITS
    鮮
    0.07
    *-
    0.07
    ā
    0.06
    ":"","
    0.06
    Boolean
    0.06
     <:
    0.06
    Mark
    0.06
     comando
    0.06
    结合
    0.06
    _facebook
    0.06
    Act Density 0.265%

    No Known Activations