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

    Neuronpedia

    INDEX
    Explanations

    company acquisitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ak
    -0.06
    ,
↵
↵
    -0.06
    :
↵
↵
    -0.06
    NOT
    -0.06
     conting
    -0.06
    Classes
    -0.06
    рения
    -0.06
     EAST
    -0.06
    _COOKIE
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     keyed
    0.07
     ".
    0.06
     habitual
    0.06
     Custom
    0.06
    authorize
    0.06
    unteers
    0.06
     ranged
    0.06
     put
    0.06
    wx
    0.06
     Pri
    0.06
    Act Density 0.019%

    No Known Activations