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

    Neuronpedia

    INDEX
    Explanations

    loneliness and medical conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ва
    0.49
    자
    0.47
    리
    0.46
    则
    0.45
    Jon
    0.45
    а
    0.45
    肉
    0.45
    alcohol
    0.44
    Jo
    0.44
    龙
    0.44
    POSITIVE LOGITS
     faulty
    0.53
     tacit
    0.46
     intim
    0.45
     stunned
    0.44
     doigts
    0.44
     despre
    0.44
     young
    0.44
     dysfunctional
    0.43
     consummate
    0.42
     studios
    0.42
    Act Density 0.001%

    No Known Activations