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

    Neuronpedia

    INDEX
    Explanations

    speaking. or thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ale
    0.87
     impairment
    0.81
    ia
    0.80
     eventuali
    0.79
     skilful
    0.79
     omission
    0.78
     تاثیر
    0.77
     tangible
    0.76
     understatement
    0.76
     traceability
    0.76
    POSITIVE LOGITS
    פ
    0.82
    ﻮ
    0.82
    Cancer
    0.81
    Ს
    0.81
    ﺮ
    0.80
    0.80
    Datos
    0.78
    GOD
    0.78
    Clin
    0.78
    Hibernate
    0.78
    Act Density 0.001%

    No Known Activations