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

    Neuronpedia

    INDEX
    Explanations

    select item or area

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.78
    in
    0.68
     to
    0.63
     with
    0.56
    ley
    0.55
    _
    0.55
    /
    0.55
     id
    0.54
     using
    0.54
     colored
    0.52
    POSITIVE LOGITS
    ると
    0.63
     Ouvrard
    0.60
    Brussels
    0.60
     Rockland
    0.60
    管理
    0.59
     ruke
    0.59
    \<^
    0.59
     deven
    0.57
     westerly
    0.57
    サービスの
    0.57
    Act Density 0.020%

    No Known Activations