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

    Neuronpedia

    INDEX
    Explanations

    can cause negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    带动
    0.81
     influenz
    0.78
     påver
    0.76
    onium
    0.75
     Affect
    0.75
     zmienia
    0.75
     wpły
    0.74
     perubahan
    0.74
     Changing
    0.72
     cambiar
    0.72
    POSITIVE LOGITS
    未能
    0.90
     insufficiently
    0.88
     belated
    0.88
     largely
    0.83
     failed
    0.81
     balk
    0.80
     increasingly
    0.79
     manifestly
    0.79
     fail
    0.78
     fails
    0.77
    Act Density 0.316%

    No Known Activations