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

    Neuronpedia

    INDEX
    Explanations

    words forming phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kal
    0.45
     ganzen
    0.41
     นัก
    0.40
    NESS
    0.39
     조
    0.39
     metabolized
    0.39
     kur
    0.39
    ectar
    0.38
    oshi
    0.38
     ja
    0.38
    POSITIVE LOGITS
    يمق
    0.50
    های
    0.49
    ینګ
    0.47
     ocasion
    0.47
     anecd
    0.46
    motivated
    0.46
     autograph
    0.44
    ändert
    0.44
     alerting
    0.43
    ږد
    0.43
    Act Density 0.000%

    No Known Activations