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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.73
    TestingModule
    -0.69
     betweenstory
    -0.57
     geweest
    -0.56
     gehouden
    -0.55
     gehad
    -0.53
     valgt
    -0.53
     tevreden
    -0.52
     Tem
    -0.50
     périph
    -0.50
    POSITIVE LOGITS
     may
    0.63
     actionMode
    0.62
     can
    0.61
     range
    0.58
    LookAnd
    0.56
     propOrder
    0.55
     drift
    0.54
     explode
    0.53
     continue
    0.52
     fhew
    0.52
    Act Density 0.014%

    No Known Activations