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

    Neuronpedia

    INDEX
    Explanations

    legal, software licenses, victims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.69
     Straight
    -0.64
    Straight
    -0.63
    straight
    -0.60
     straight
    -0.60
     snippetHide
    -0.57
    kháu
    -0.54
    
    -0.54
    Demografia
    -0.53
     MemoryStream
    -0.52
    POSITIVE LOGITS
     Persons
    0.56
     persons
    0.54
    UserScript
    0.51
     PERSONS
    0.47
    Personensuche
    0.47
     presidency
    0.47
     perfons
    0.47
     Misa
    0.47
    Persons
    0.45
     endforeach
    0.45
    Act Density 0.000%

    No Known Activations