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

    Neuronpedia

    INDEX
    Explanations

    same counting years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ോട്ട്
    0.43
    agregar
    0.42
     Agregar
    0.41
     Están
    0.41
    നിയ
    0.41
    ोत्
    0.40
     negeri
    0.40
     estarán
    0.40
    ಂಗ
    0.40
    சர்
    0.39
    POSITIVE LOGITS
     munc
    0.40
    Wage
    0.39
     income
    0.39
     வருவத
    0.38
     depres
    0.38
    .
    0.37
     palm
    0.36
     Jacoby
    0.36
     crem
    0.36
     mistakenly
    0.35
    Act Density 0.001%

    No Known Activations