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

    Neuronpedia

    INDEX
    Explanations

    factors influencing situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boek
    0.59
     dvě
    0.57
     twee
    0.55
     álbum
    0.55
     välja
    0.55
     excruciating
    0.55
     deux
    0.54
     dieci
    0.54
     két
    0.54
     Fáb
    0.53
    POSITIVE LOGITS
     influences
    1.20
     влияет
    1.15
     factors
    1.11
     influence
    1.10
     influencing
    1.08
    因素
    1.07
     influencia
    0.98
     повлия
    0.97
     влия
    0.96
     впли
    0.96
    Act Density 0.005%

    No Known Activations