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

    Neuronpedia

    INDEX
    Explanations

    Mark followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Urb
    0.43
     ref
    0.41
    etière
    0.40
     patient
    0.40
     Guinea
    0.40
    ធ
    0.39
    ल्पना
    0.38
    পত্রের
    0.38
    romechanical
    0.38
     Refer
    0.37
    POSITIVE LOGITS
     Sto
    0.44
     sto
    0.43
    Sto
    0.39
    Sterling
    0.39
    MER
    0.39
     MER
    0.38
    テンプレート
    0.38
     Heer
    0.37
    Mer
    0.37
    Logan
    0.36
    Act Density 0.001%

    No Known Activations