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

    Neuronpedia

    INDEX
    Explanations

    stereotype

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Staff
    1.07
     Staff
    1.01
     staff
    0.98
     STAFF
    0.93
    synthetic
    0.85
     estando
    0.84
    یر
    0.82
    στο
    0.81
     sociétés
    0.81
     estaría
    0.80
    POSITIVE LOGITS
    Microelectronics
    0.89
     quo
    0.88
    การณ์
    0.83
     가
    0.83
    Errorf
    0.83
    holders
    0.82
    분의
    0.82
    dard
    0.81
    eroom
    0.81
    AsFactors
    0.80
    Act Density 1.111%

    No Known Activations