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

    Neuronpedia

    INDEX
    Explanations

    on with or on to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Incoming
    0.45
     Brings
    0.43
     Away
    0.42
     Doremi
    0.42
    矚
    0.41
     Dedicated
    0.40
     Account
    0.40
     styleUrls
    0.40
    driven
    0.39
    Mal
    0.38
    POSITIVE LOGITS
    estep
    0.53
    н
    0.50
    ibilidad
    0.48
     to
    0.47
    чи
    0.47
    х
    0.47
    чили
    0.46
     autopilot
    0.46
     ho
    0.45
     siis
    0.44
    Act Density 0.007%

    No Known Activations