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

    Neuronpedia

    INDEX
    Explanations

    specific professional entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pueden
    0.42
    yout
    0.41
     وسلم
    0.41
    ników
    0.41
     suerte
    0.40
    ysm
    0.40
    kup
    0.40
    ysuckle
    0.40
    STRONG
    0.40
     familias
    0.39
    POSITIVE LOGITS
    Japan
    0.44
    Professional
    0.42
     professional
    0.41
    professional
    0.40
    Sweden
    0.39
    Howard
    0.38
    mnist
    0.37
     pioneer
    0.36
     Professional
    0.35
     Sweden
    0.35
    Act Density 0.000%

    No Known Activations