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

    Neuronpedia

    INDEX
    Explanations

    the reader or viewer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     colleagues
    -0.98
     بیم
    -0.97
    fans
    -0.88
     peers
    -0.88
     Opin
    -0.85
     hastal
    -0.84
     getUsers
    -0.84
    patients
    -0.83
    itoriale
    -0.82
     anderen
    -0.82
    POSITIVE LOGITS
     reader
    2.64
     viewer
    2.63
     listener
    2.45
     user
    2.25
     wearer
    2.08
     buyer
    2.02
    utilisateur
    1.80
     visitor
    1.72
     purchaser
    1.71
     learner
    1.70
    Act Density 0.128%

    No Known Activations