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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sun
    -0.07
    vanized
    -0.07
    -i
    -0.07
     Rift
    -0.07
    豆
    -0.07
    arya
    -0.07
    _bbox
    -0.06
    movement
    -0.06
    Polygon
    -0.06
     electronically
    -0.06
    POSITIVE LOGITS
    _".$
    0.06
     εγκα
    0.06
    .PARAM
    0.06
    terrorism
    0.06
    ."));↵
    0.06
     escape
    0.06
     Vlad
    0.06
    鳴
    0.06
    ();
↵
    0.06
     δη
    0.06
    Act Density 0.077%

    No Known Activations