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

    Neuronpedia

    INDEX
    Explanations

    System

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RECT
    -0.06
    xiety
    -0.06
    	dst
    -0.06
    òng
    -0.06
     Kaiser
    -0.06
    agh
    -0.06
     dicks
    -0.06
    -resources
    -0.06
    andFilterWhere
    -0.06
    wife
    -0.06
    POSITIVE LOGITS
    .bean
    0.07
    �장
    0.07
    ’.
    0.06
    ieber
    0.06
     Normally
    0.06
    ”.
    0.06
    嫌
    0.06
     acts
    0.06
    .toJson
    0.06
    ?,
    0.06
    Act Density 0.003%

    No Known Activations