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

    Neuronpedia

    INDEX
    Explanations

    tune, variety, relationships, safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     God
    0.44
     Press
    0.38
    endi
    0.38
     Kandid
    0.37
     Coat
    0.37
     Adi
    0.37
     GOD
    0.36
     admi
    0.36
     Bentley
    0.36
     Tab
    0.35
    POSITIVE LOGITS
    堈
    0.42
     achat
    0.38
    ইয়
    0.37
    古
    0.37
    ouchers
    0.37
    釟
    0.37
    不变
    0.37
    Payments
    0.36
    ческим
    0.36
    JRE
    0.36
    Act Density 0.000%

    No Known Activations