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

    Neuronpedia

    INDEX
    Explanations

    mechanical parts and motion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     UVB
    1.09
     ફો
    1.00
     Bharti
    0.96
    Benzo
    0.95
    fstream
    0.94
     notificación
    0.93
    資格
    0.91
     ASCII
    0.90
     promoc
    0.90
     Telefon
    0.89
    POSITIVE LOGITS
     mechanical
    1.58
    mechanical
    1.43
     machinery
    1.36
     mechanics
    1.32
     Mechanical
    1.31
     wheels
    1.30
    Mechanical
    1.30
     engines
    1.28
    wheels
    1.27
     axles
    1.26
    Act Density 0.129%

    No Known Activations