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

    Neuronpedia

    INDEX
    Explanations

    lessen, diminish, suggests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Architecture
    0.38
    ffen
    0.38
    blk
    0.38
    Originally
    0.38
    Ammo
    0.37
    Happ
    0.37
    Combining
    0.37
    Sincerely
    0.37
    DOCTYPE
    0.37
    ،
    0.36
    POSITIVE LOGITS
     경
    0.61
     sospe
    0.50
    經
    0.50
    ຫານ
    0.49
     अहम
    0.47
     closet
    0.47
    adas
    0.46
     CHEM
    0.45
     kendisine
    0.45
     suspe
    0.45
    Act Density 0.001%

    No Known Activations