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

    Neuronpedia

    INDEX
    Explanations

    destruction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     других
    -0.08
    lke
    -0.08
    learn
    -0.07
    ocrine
    -0.07
    ㌽
    -0.07
     общественно
    -0.07
    $insert
    -0.07
    -known
    -0.06
    firstname
    -0.06
    /')
    -0.06
    POSITIVE LOGITS
     radiant
    0.07
    スー�
    0.07
    terror
    0.07
    羌
    0.07
    awks
    0.07
    avez
    0.07
    较强的
    0.07
    改善
    0.07
     clutch
    0.06
    无比
    0.06
    Act Density 0.072%

    No Known Activations