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

    Neuronpedia

    INDEX
    Explanations

    action verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    featureID
    -0.84
     nahilalakip
    -0.59
    styleType
    -0.56
    ỏng
    -0.51
     the
    -0.50
     conmigo
    -0.50
     MEANS
    -0.50
    knapp
    -0.50
    usky
    -0.50
    ỡng
    -0.49
    POSITIVE LOGITS
     which
    0.57
     where
    0.50
    
    0.50
    AndroidJUnit
    0.50
    IsContent
    0.49
     wohin
    0.49
    bitField
    0.47
     kubwa
    0.46
    inhua
    0.45
    UserRepository
    0.45
    Act Density 0.003%

    No Known Activations