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

    Neuronpedia

    INDEX
    Explanations

    accessing your information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     δεν
    1.23
     slander
    1.06
    но
    1.05
     freehold
    1.02
     wasn
    1.01
     hasn
    1.01
    finals
    1.01
    aadhar
    1.01
     arrogance
    0.99
     acquittal
    0.99
    POSITIVE LOGITS
    s
    1.10
    نم
    1.05
     Examine
    1.02
     பிறகு
    0.98
     primeros
    0.98
    teile
    0.97
     Spare
    0.97
    atoshi
    0.97
    te
    0.96
    tered
    0.96
    Act Density 0.001%

    No Known Activations