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

    Neuronpedia

    INDEX
    Explanations

    cunning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    region
    -0.07
     �
    -0.07
    .percent
    -0.07
     Reaction
    -0.06
    lehem
    -0.06
     reflux
    -0.06
    аф
    -0.06
     reactions
    -0.06
    мет
    -0.06
    ليم
    -0.06
    POSITIVE LOGITS
     cunning
    0.14
     Cunning
    0.10
     sly
    0.07
     така
    0.07
     Curtis
    0.07
    []>
    0.06
     Độ
    0.06
    İN
    0.06
    .TXT
    0.06
    628
    0.06
    Act Density 0.003%

    No Known Activations