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

    Neuronpedia

    INDEX
    Explanations

    your + title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hemicontinuous
    0.38
     anului
    0.38
    Stages
    0.37
     bukti
    0.37
    buat
    0.37
    DeathRecord
    0.37
     HIS
    0.36
    বিদ্যা
    0.36
    his
    0.36
    obenzene
    0.35
    POSITIVE LOGITS
     Highness
    0.88
     Majesty
    0.86
     majesty
    0.80
     Holiness
    0.80
     holiness
    0.77
    Maj
    0.72
     Excellency
    0.70
     Maj
    0.70
     Emin
    0.68
     majest
    0.68
    Act Density 0.003%

    No Known Activations